Quick Answer: Intel Arc Pro A40 offers 6GB VRAM and starts around current market pricing. It delivers approximately 66 tokens/sec on Deepseek AI Deepseek Ocr 2. It typically draws 50W under load.
This GPU offers reliable throughput for local AI workloads. Pair it with the right model quantization to hit your desired tokens/sec, and monitor prices below to catch the best deal.
With 6GB VRAM, Intel Arc Pro A40 can run models up to approximately 15B parameters using 4-bit quantization. Consider quantization or smaller models for best results.
Consider RTX 4060 or higher — Next tier offers meaningful improvement.
Showing 80 of 80 benchmark rows.
| Model | Size | Quantization | Tokens/sec | VRAM used |
|---|---|---|---|---|
| Deepseek AI Deepseek Ocr 2 | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek Math V2 | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek V2 5 | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek V3 | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Deepseek AI Deepseek Coder V2 Lite Instruct | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek V3.1 | Unknown | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Deepseek AI Deepseek Coder 1.3B Instruct | 1.3B | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek R1 Distill Qwen 1.5B | 1.5B | Q4 | 66.29 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Deepseek AI Deepseek Ocr | Unknown | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 8bit | 8B | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 4bit | 8B | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Deepseek AI Deepseek R1 | Unknown | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Deepseek AI Deepseek R1 0528 | Unknown | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Deepseek AI Deepseek R1 Distill Llama 8B | 8B | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Deepseek AI Deepseek R1 Distill Qwen 7B | 7B | Q4 | 55.25 tok/sEstimated Static estimation (DB-independent) | 4GB |
| Nineninesix Kani Tts 2 En | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Nanbeige Nanbeige4 1 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Minimaxai Minimax M2 5 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Minimaxai Minimax M2 1 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Stepfun AI Step 3 5 Flash | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Qwen Qwen3 Coder Next | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Moonshotai Kimi K2 5 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Xiaomimimo Mimo V2 Flash | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Nari Labs Dia2 2B | 2B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Google Embeddinggemma 300M | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Facebook Sam3 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Black Forest Labs Flux 2 Dev | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Moonshotai Kimi K2 Thinking | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Microsoft Phi 3 5 Mini Instruct | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Meta Llama Llama 3 2 3B Instruct | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Qwen Qwen3 1.7B Base | 1.7B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Dicta Il Dictalm2.0 Instruct | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2 0.5B Instruct | 0.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Apple Openelm 1 1B Instruct | 1B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2.5 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Unsloth Gemma 3 1B It | 1B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Bigcode Starcoder2 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Ibm Granite Granite Docling 258M | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Skt Kogpt2 Base V2 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Google Gemma 3 270M It | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Eleutherai Pythia 70M Deduped | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Microsoft Vibevoice 1.5B | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Ibm Granite Granite 3.3 2B Instruct | 2B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Google Gemma 2B | 2B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Trl Internal Testing Tiny Llamaforcausallm 3.2 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Llamafactory Tiny Random Llama 3 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Unsloth Llama 3.2 1B Instruct | 1B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Numind Nuextract 1.5 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Hmellor Tiny Random Llamaforcausallm | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Sshleifer Tiny Gpt2 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Openai Community Gpt2 Xl | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Ibm Research Powermoe 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Unsloth Llama 3.2 3B Instruct | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Meta Llama Llama 3.2 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Eleutherai Gpt Neo 125M | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Meta Llama Llama Guard 3 1B | 1B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2 1.5B Instruct | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Google Gemma 2 2B It | 2B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Microsoft Phi 3.5 Mini Instruct | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Microsoft Phi 3.5 Vision Instruct | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Rinna Japanese Gpt Neox Small | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2.5 Coder 1.5B | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Microsoft Dialogpt Small | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen3 0.6B Base | 0.6B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Openai Community Gpt2 Medium | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Trl Internal Testing Tiny Random Llamaforcausallm | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2.5 Math 1.5B | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Huggingfacetb Smollm 135M | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Liquidai Lfm2 1.2B | 1.2B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2 0.5B | 0.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Minimaxai Minimax M2 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Huggingfacetb Smollm2 135M | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Microsoft Phi 2 | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2.5 0.5B | 0.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen2.5 1.5B | 1.5B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Qwen Qwen3 Reranker 0.6B | 0.6B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Google T5 T5 3B | 3B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 2GB |
| Qwen Qwen3 1.7B | 1.7B | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
| Openai Community Gpt2 Large | Unknown | Q4 | 53.04 tok/sEstimated Static estimation (DB-independent) | 1GB |
Showing 240 of 240 compatibility rows.
| Model | Size | Quantization | Verdict | Estimated speed | VRAM needed |
|---|---|---|---|---|---|
| 01 AI Yi 1 5 34B Chat | 34B | Q4 | Not supported | 15.47 tok/sEstimated | 17GB (have 6GB) |
| 01 AI Yi 1 5 34B Chat | 34B | Q8 | Not supported | 10.83 tok/sEstimated | 34GB (have 6GB) |
| 01 AI Yi 1 5 34B Chat | 34B | FP16 | Not supported | 5.88 tok/sEstimated | 68GB (have 6GB) |
| AI Forever Rugpt 3.5 13B | 13B | Q4 | Not supported | 33.15 tok/sEstimated | 7GB (have 6GB) |
| AI Forever Rugpt 3.5 13B | 13B | Q8 | Not supported | 23.20 tok/sEstimated | 13GB (have 6GB) |
| AI Forever Rugpt 3.5 13B | 13B | FP16 | Not supported | 12.60 tok/sEstimated | 26GB (have 6GB) |
| AI Mo Kimina Prover 72B | 72B | Q4 | Not supported | 8.84 tok/sEstimated | 36GB (have 6GB) |
| AI Mo Kimina Prover 72B | 72B | Q8 | Not supported | 6.19 tok/sEstimated | 72GB (have 6GB) |
| AI Mo Kimina Prover 72B | 72B | FP16 | Not supported | 3.36 tok/sEstimated | 144GB (have 6GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 3GB (have 6GB) |
| Allenai Olmo 2 0425 1B | 1B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Allenai Olmo 2 0425 1B | 1B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Allenai Olmo 2 0425 1B | 1B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 2GB (have 6GB) |
| Allenai Olmo 3 7B Think | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Allenai Olmo 3 7B Think | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Allenai Olmo 3 7B Think | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Apple Openelm 1 1B Instruct | 1B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Apple Openelm 1 1B Instruct | 1B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Apple Openelm 1 1B Instruct | 1B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 3GB (have 6GB) |
| Baichuan Inc Baichuan M2 32B | 32B | Q4 | Not supported | 15.47 tok/sEstimated | 16GB (have 6GB) |
| Baichuan Inc Baichuan M2 32B | 32B | Q8 | Not supported | 10.83 tok/sEstimated | 32GB (have 6GB) |
| Baichuan Inc Baichuan M2 32B | 32B | FP16 | Not supported | 5.88 tok/sEstimated | 64GB (have 6GB) |
| Bigcode Starcoder2 3B | 3B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Bigcode Starcoder2 3B | 3B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Bigcode Starcoder2 3B | 3B | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Bigscience Bloomz 560M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Bigscience Bloomz 560M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Bigscience Bloomz 560M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 2GB (have 6GB) |
| Black Forest Labs Flux 1 Dev | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Black Forest Labs Flux 1 Dev | Unknown | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Black Forest Labs Flux 1 Dev | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Black Forest Labs Flux 2 Dev | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Black Forest Labs Flux 2 Dev | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Black Forest Labs Flux 2 Dev | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Bsc Lt Salamandrata 7B Instruct | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Bsc Lt Salamandrata 7B Instruct | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Bsc Lt Salamandrata 7B Instruct | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Codellama Codellama 34B HF | 34B | Q4 | Not supported | 15.47 tok/sEstimated | 17GB (have 6GB) |
| Codellama Codellama 34B HF | 34B | Q8 | Not supported | 10.83 tok/sEstimated | 34GB (have 6GB) |
| Codellama Codellama 34B HF | 34B | FP16 | Not supported | 5.88 tok/sEstimated | 68GB (have 6GB) |
| Context Labs Meta Llama Llama 3.2 3B Instruct FP16 | 3B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Context Labs Meta Llama Llama 3.2 3B Instruct FP16 | 3B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Context Labs Meta Llama Llama 3.2 3B Instruct FP16 | 3B | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Deepseek AI Deepseek Coder 1.3B Instruct | 1.3B | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek Coder 1.3B Instruct | 1.3B | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek Coder 1.3B Instruct | 1.3B | FP16 | Fits comfortably | 25.19 tok/sEstimated | 3GB (have 6GB) |
| Deepseek AI Deepseek Coder 33B Instruct | 33B | Q4 | Not supported | 19.34 tok/sEstimated | 17GB (have 6GB) |
| Deepseek AI Deepseek Coder 33B Instruct | 33B | Q8 | Not supported | 13.54 tok/sEstimated | 33GB (have 6GB) |
| Deepseek AI Deepseek Coder 33B Instruct | 33B | FP16 | Not supported | 7.35 tok/sEstimated | 66GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Instruct 0724 | Unknown | Q4 | Not supported | 11.05 tok/sEstimated | 36GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Instruct 0724 | Unknown | Q8 | Not supported | 7.73 tok/sEstimated | 72GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Instruct 0724 | Unknown | FP16 | Not supported | 4.20 tok/sEstimated | 144GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Lite Instruct | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Lite Instruct | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek Coder V2 Lite Instruct | Unknown | FP16 | Fits comfortably | 25.19 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek Math V2 | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek Math V2 | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek Math V2 | Unknown | FP16 | Fits comfortably | 25.19 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek Ocr | Unknown | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek Ocr | Unknown | Q8 | Not supported | 38.67 tok/sEstimated | 7GB (have 6GB) |
| Deepseek AI Deepseek Ocr | Unknown | FP16 | Not supported | 20.99 tok/sEstimated | 14GB (have 6GB) |
| Deepseek AI Deepseek Ocr 2 | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek Ocr 2 | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek Ocr 2 | Unknown | FP16 | Fits comfortably | 25.19 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek R1 | Unknown | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek R1 | Unknown | Q8 | Not supported | 38.67 tok/sEstimated | 7GB (have 6GB) |
| Deepseek AI Deepseek R1 | Unknown | FP16 | Not supported | 20.99 tok/sEstimated | 14GB (have 6GB) |
| Deepseek AI Deepseek R1 0528 | Unknown | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek R1 0528 | Unknown | Q8 | Not supported | 38.67 tok/sEstimated | 8GB (have 6GB) |
| Deepseek AI Deepseek R1 0528 | Unknown | FP16 | Not supported | 20.99 tok/sEstimated | 16GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Llama 8B | 8B | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Llama 8B | 8B | Q8 | Not supported | 38.67 tok/sEstimated | 8GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Llama 8B | 8B | FP16 | Not supported | 20.99 tok/sEstimated | 16GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 1.5B | 1.5B | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 1.5B | 1.5B | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 1.5B | 1.5B | FP16 | Fits comfortably | 25.19 tok/sEstimated | 3GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 32B | 32B | Q4 | Not supported | 19.34 tok/sEstimated | 16GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 32B | 32B | Q8 | Not supported | 13.54 tok/sEstimated | 32GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 32B | 32B | FP16 | Not supported | 7.35 tok/sEstimated | 64GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 7B | 7B | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 7B | 7B | Q8 | Not supported | 38.67 tok/sEstimated | 7GB (have 6GB) |
| Deepseek AI Deepseek R1 Distill Qwen 7B | 7B | FP16 | Not supported | 20.99 tok/sEstimated | 14GB (have 6GB) |
| Deepseek AI Deepseek V2 5 | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 1GB (have 6GB) |
| Deepseek AI Deepseek V2 5 | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek V2 5 | Unknown | FP16 | Fits comfortably | 25.19 tok/sEstimated | 4GB (have 6GB) |
| Deepseek AI Deepseek V3 | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek V3 | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 3GB (have 6GB) |
| Deepseek AI Deepseek V3 | Unknown | FP16 | Fits (tight) | 25.19 tok/sEstimated | 6GB (have 6GB) |
| Deepseek AI Deepseek V3 0324 | Unknown | Q4 | Not supported | 19.34 tok/sEstimated | 16GB (have 6GB) |
| Deepseek AI Deepseek V3 0324 | Unknown | Q8 | Not supported | 13.54 tok/sEstimated | 32GB (have 6GB) |
| Deepseek AI Deepseek V3 0324 | Unknown | FP16 | Not supported | 7.35 tok/sEstimated | 64GB (have 6GB) |
| Deepseek AI Deepseek V3.1 | Unknown | Q4 | Fits comfortably | 66.29 tok/sEstimated | 2GB (have 6GB) |
| Deepseek AI Deepseek V3.1 | Unknown | Q8 | Fits comfortably | 46.41 tok/sEstimated | 3GB (have 6GB) |
| Deepseek AI Deepseek V3.1 | Unknown | FP16 | Fits (tight) | 25.19 tok/sEstimated | 6GB (have 6GB) |
| Dicta Il Dictalm2.0 Instruct | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Dicta Il Dictalm2.0 Instruct | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Dicta Il Dictalm2.0 Instruct | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Distilbert Distilgpt2 | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Distilbert Distilgpt2 | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Distilbert Distilgpt2 | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Dphn Dolphin 2.9.1 Yi 1.5 34B | 34B | Q4 | Not supported | 15.47 tok/sEstimated | 17GB (have 6GB) |
| Dphn Dolphin 2.9.1 Yi 1.5 34B | 34B | Q8 | Not supported | 10.83 tok/sEstimated | 34GB (have 6GB) |
| Dphn Dolphin 2.9.1 Yi 1.5 34B | 34B | FP16 | Not supported | 5.88 tok/sEstimated | 68GB (have 6GB) |
| Eleutherai Gpt Neo 125M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Eleutherai Gpt Neo 125M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Eleutherai Gpt Neo 125M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Eleutherai Pythia 70M Deduped | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Eleutherai Pythia 70M Deduped | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Eleutherai Pythia 70M Deduped | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Essentialai Rnj 1 | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Essentialai Rnj 1 | Unknown | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Essentialai Rnj 1 | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Facebook Opt 125M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Facebook Opt 125M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Facebook Opt 125M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Facebook Sam3 | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Facebook Sam3 | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Facebook Sam3 | Unknown | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Fireredteam Firered Image Edit 1 0 | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Fireredteam Firered Image Edit 1 0 | Unknown | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Fireredteam Firered Image Edit 1 0 | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Gensyn Qwen2.5 0.5B Instruct | 0.5B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Gensyn Qwen2.5 0.5B Instruct | 0.5B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Gensyn Qwen2.5 0.5B Instruct | 0.5B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Google Bert Bert Base Uncased | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Google Bert Bert Base Uncased | Unknown | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Google Bert Bert Base Uncased | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Google Embeddinggemma 300M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Google Embeddinggemma 300M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Google Embeddinggemma 300M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 2 27B It | 27B | Q4 | Not supported | 24.31 tok/sEstimated | 14GB (have 6GB) |
| Google Gemma 2 27B It | 27B | Q8 | Not supported | 17.02 tok/sEstimated | 27GB (have 6GB) |
| Google Gemma 2 27B It | 27B | FP16 | Not supported | 9.24 tok/sEstimated | 54GB (have 6GB) |
| Google Gemma 2 2B It | 2B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 2 2B It | 2B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Google Gemma 2 2B It | 2B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Google Gemma 2 9B It | 9B | Q4 | Fits (tight) | 33.15 tok/sEstimated | 5GB (have 6GB) |
| Google Gemma 2 9B It | 9B | Q8 | Not supported | 23.20 tok/sEstimated | 9GB (have 6GB) |
| Google Gemma 2 9B It | 9B | FP16 | Not supported | 12.60 tok/sEstimated | 18GB (have 6GB) |
| Google Gemma 2B | 2B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 2B | 2B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Google Gemma 2B | 2B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Google Gemma 3 1B It | 1B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 3 1B It | 1B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 3 1B It | 1B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 2GB (have 6GB) |
| Google Gemma 3 270M It | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 3 270M It | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Google Gemma 3 270M It | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Google T5 T5 3B | 3B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Google T5 T5 3B | 3B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Google T5 T5 3B | 3B | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Gsai Ml Llada 8B Base | 8B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Gsai Ml Llada 8B Base | 8B | Q8 | Not supported | 30.94 tok/sEstimated | 8GB (have 6GB) |
| Gsai Ml Llada 8B Base | 8B | FP16 | Not supported | 16.79 tok/sEstimated | 16GB (have 6GB) |
| Gsai Ml Llada 8B Instruct | 8B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Gsai Ml Llada 8B Instruct | 8B | Q8 | Not supported | 30.94 tok/sEstimated | 8GB (have 6GB) |
| Gsai Ml Llada 8B Instruct | 8B | FP16 | Not supported | 16.79 tok/sEstimated | 16GB (have 6GB) |
| Hmellor Tiny Random Llamaforcausallm | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Hmellor Tiny Random Llamaforcausallm | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Hmellor Tiny Random Llamaforcausallm | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Huggingfaceh4 Zephyr 7B Beta | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Huggingfaceh4 Zephyr 7B Beta | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Huggingfaceh4 Zephyr 7B Beta | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Huggingfacem4 Tiny Random Llamaforcausallm | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Huggingfacem4 Tiny Random Llamaforcausallm | Unknown | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Huggingfacem4 Tiny Random Llamaforcausallm | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Huggingfacetb Smollm 135M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Huggingfacetb Smollm 135M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Huggingfacetb Smollm 135M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Huggingfacetb Smollm2 135M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Huggingfacetb Smollm2 135M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Huggingfacetb Smollm2 135M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Huggyllama Llama 7B | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Huggyllama Llama 7B | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Huggyllama Llama 7B | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Ibm Granite Granite 3.3 2B Instruct | 2B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Ibm Granite Granite 3.3 2B Instruct | 2B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Ibm Granite Granite 3.3 2B Instruct | 2B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 4GB (have 6GB) |
| Ibm Granite Granite 3.3 8B Instruct | 8B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Ibm Granite Granite 3.3 8B Instruct | 8B | Q8 | Not supported | 30.94 tok/sEstimated | 8GB (have 6GB) |
| Ibm Granite Granite 3.3 8B Instruct | 8B | FP16 | Not supported | 16.79 tok/sEstimated | 16GB (have 6GB) |
| Ibm Granite Granite Docling 258M | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Ibm Granite Granite Docling 258M | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 1GB (have 6GB) |
| Ibm Granite Granite Docling 258M | Unknown | FP16 | Fits comfortably | 20.15 tok/sEstimated | 1GB (have 6GB) |
| Ibm Research Powermoe 3B | 3B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Ibm Research Powermoe 3B | 3B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Ibm Research Powermoe 3B | 3B | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Ilyagusev Saiga Llama3 8B | 8B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Ilyagusev Saiga Llama3 8B | 8B | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Ilyagusev Saiga Llama3 8B | 8B | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Inference Net Schematron 3B | 3B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Inference Net Schematron 3B | 3B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Inference Net Schematron 3B | 3B | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Kaitchup Phi 3 Mini 4K Instruct Gptq 4bit | Unknown | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Kaitchup Phi 3 Mini 4K Instruct Gptq 4bit | Unknown | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Kaitchup Phi 3 Mini 4K Instruct Gptq 4bit | Unknown | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Liquidai Lfm2 1.2B | 1.2B | Q4 | Fits comfortably | 53.04 tok/sEstimated | 1GB (have 6GB) |
| Liquidai Lfm2 1.2B | 1.2B | Q8 | Fits comfortably | 37.13 tok/sEstimated | 2GB (have 6GB) |
| Liquidai Lfm2 1.2B | 1.2B | FP16 | Fits comfortably | 20.15 tok/sEstimated | 3GB (have 6GB) |
| Liuhaotian Llava V1.5 7B | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Liuhaotian Llava V1.5 7B | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Liuhaotian Llava V1.5 7B | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Llamafactory Tiny Random Llama 3 | Unknown | Q4 | Fits comfortably | 53.04 tok/sEstimated | 2GB (have 6GB) |
| Llamafactory Tiny Random Llama 3 | Unknown | Q8 | Fits comfortably | 37.13 tok/sEstimated | 3GB (have 6GB) |
| Llamafactory Tiny Random Llama 3 | Unknown | FP16 | Fits (tight) | 20.15 tok/sEstimated | 6GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 4bit | 8B | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 4bit | 8B | Q8 | Not supported | 38.67 tok/sEstimated | 8GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 4bit | 8B | FP16 | Not supported | 20.99 tok/sEstimated | 16GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 8bit | 8B | Q4 | Fits comfortably | 55.25 tok/sEstimated | 4GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 8bit | 8B | Q8 | Not supported | 38.67 tok/sEstimated | 8GB (have 6GB) |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 8bit | 8B | FP16 | Not supported | 20.99 tok/sEstimated | 16GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 4bit | 4B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 4bit | 4B | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 4bit | 4B | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 6bit | 4B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 6bit | 4B | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 6bit | 4B | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 8bit | 4B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 2GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 8bit | 4B | Q8 | Fits comfortably | 30.94 tok/sEstimated | 4GB (have 6GB) |
| Lmstudio Community Qwen3 4B Thinking 2507 Mlx 8bit | 4B | FP16 | Not supported | 16.79 tok/sEstimated | 8GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 4bit | 30B | Q4 | Not supported | 24.31 tok/sEstimated | 15GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 4bit | 30B | Q8 | Not supported | 17.02 tok/sEstimated | 30GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 4bit | 30B | FP16 | Not supported | 9.24 tok/sEstimated | 60GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 5bit | 30B | Q4 | Not supported | 24.31 tok/sEstimated | 15GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 5bit | 30B | Q8 | Not supported | 17.02 tok/sEstimated | 30GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 5bit | 30B | FP16 | Not supported | 9.24 tok/sEstimated | 60GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 6bit | 30B | Q4 | Not supported | 24.31 tok/sEstimated | 15GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 6bit | 30B | Q8 | Not supported | 17.02 tok/sEstimated | 30GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 6bit | 30B | FP16 | Not supported | 9.24 tok/sEstimated | 60GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 8bit | 30B | Q4 | Not supported | 24.31 tok/sEstimated | 15GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 8bit | 30B | Q8 | Not supported | 17.02 tok/sEstimated | 30GB (have 6GB) |
| Lmstudio Community Qwen3 Coder 30B A3b Instruct Mlx 8bit | 30B | FP16 | Not supported | 9.24 tok/sEstimated | 60GB (have 6GB) |
| Lmsys Vicuna 7B V1.5 | 7B | Q4 | Fits comfortably | 44.20 tok/sEstimated | 4GB (have 6GB) |
| Lmsys Vicuna 7B V1.5 | 7B | Q8 | Not supported | 30.94 tok/sEstimated | 7GB (have 6GB) |
| Lmsys Vicuna 7B V1.5 | 7B | FP16 | Not supported | 16.79 tok/sEstimated | 14GB (have 6GB) |
| Meta Llama Llama 2 13B Chat HF | 13B | Q4 | Not supported | 33.15 tok/sEstimated | 7GB (have 6GB) |
| Meta Llama Llama 2 13B Chat HF | 13B | Q8 | Not supported | 23.20 tok/sEstimated | 13GB (have 6GB) |
| Meta Llama Llama 2 13B Chat HF | 13B | FP16 | Not supported | 12.60 tok/sEstimated | 26GB (have 6GB) |
Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data
Buy directly on Amazon with fast shipping and reliable customer service.
Essential accessories to pair with Intel Arc Pro A40
Total Bundle Price
All items from Amazon
💡 Not ready to buy? Try cloud GPUs first
Test Intel Arc Pro A40 performance in the cloud before investing in hardware. Pay by the hour with no commitment.
Explore how RTX 4090 stacks up for local inference workloads.
Explore how RTX 4080 stacks up for local inference workloads.
Explore how RTX 4070 Ti stacks up for local inference workloads.
Explore how RTX 3090 stacks up for local inference workloads.
Explore how RX 7900 XTX stacks up for local inference workloads.
Action Adventure • 2015
RPG • 2015
Battle Royale • 2017
Strategy • 2021
FPS • 2022
FPS • 2017
Action RPG • 2016
Action Adventure • 2023
Survival • 2022
Action RPG • 2020
Action • 2022
Sports • 2024