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.
Quick Answer: NVIDIA H100 PCIe 80GB has 80GB VRAM, enough for models up to roughly 200B parameters at 4-bit quantization. It draws 350W under load.
With 80GB VRAM, NVIDIA H100 PCIe 80GB can run models up to approximately 200B parameters using 4-bit quantization. That covers most popular models, including 70B-class ones at 4-bit.
Consider H100 or MI300X — Maximum VRAM for enterprise workloads.
Buy directly on Amazon with fast shipping and reliable customer service.
Essential accessories to pair with NVIDIA H100 PCIe 80GB
Accessories Total
Typical prices — check Amazon for current pricing
💡 Not ready to buy? Try cloud GPUs first
Test NVIDIA H100 PCIe 80GB performance in the cloud before investing in hardware. Pay by the hour with no commitment.
Showing 12 of 80 rows. Speeds are calculated estimates, not measurements — search for your model to jump straight to it.
| Model | Size | Quantization | Tokens/sec | VRAM used |
|---|---|---|---|---|
| Deepseek AI Deepseek Coder 1.3B Instruct | 1.3B | Q4 | ~470 tok/sEstimated | 1GB |
| Deepseek AI Deepseek R1 Distill Qwen 1.5B | 1.5B | Q4 | ~470 tok/sEstimated | 1GB |
| Deepseek AI Deepseek Ocr 2 | Unknown | Q4 | ~395 tok/sEstimated | 2GB |
| Deepseek AI Deepseek Ocr | Unknown | Q4 | ~395 tok/sEstimated | 2GB |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 8bit | 8B | Q4 | ~395 tok/sEstimated | 4GB |
| Lmstudio Community Deepseek R1 0528 Qwen3 8B Mlx 4bit | 8B | Q4 | ~395 tok/sEstimated | 4GB |
| Deepseek AI Deepseek R1 Distill Qwen 7B | 7B | Q4 | ~395 tok/sEstimated | 4GB |
| Nineninesix Kani Tts 2 En | Unknown | Q4 | ~375 tok/sEstimated | 1GB |
| Qwen Qwen3 Tts 12hz 1 7B Customvoice | 7B | Q4 | ~375 tok/sEstimated | 1GB |
| Zai Org Glm Ocr | Unknown | Q4 | ~375 tok/sEstimated | 1GB |
| Qwen Qwen3 Asr 1 7B | 7B | Q4 | ~375 tok/sEstimated | 2GB |
| Nari Labs Dia2 2B | 2B | Q4 | ~375 tok/sEstimated | 1GB |
Showing 12 of 240 rows.
| Model | Size | Quantization | Verdict | Estimated speed | VRAM needed |
|---|---|---|---|---|---|
| 01 AI Yi 1 5 34B Chat | 34B | Q4 | Fits comfortably | ~110 tok/sEstimated | 18GB (have 80GB) |
| 01 AI Yi 1 5 34B Chat | 34B | Q8 | Fits comfortably | ~77 tok/sEstimated | 35GB (have 80GB) |
| 01 AI Yi 1 5 34B Chat | 34B | FP16 | Fits comfortably | ~42 tok/sEstimated | 69GB (have 80GB) |
| AI Forever Rugpt 3.5 13B | 13B | Q4 | Fits comfortably | ~235 tok/sEstimated | 7GB (have 80GB) |
| AI Forever Rugpt 3.5 13B | 13B | Q8 | Fits comfortably | ~165 tok/sEstimated | 13GB (have 80GB) |
| AI Forever Rugpt 3.5 13B | 13B | FP16 | Fits comfortably | ~90 tok/sEstimated | 26GB (have 80GB) |
| AI Mo Kimina Prover 72B | 72B | Q4 | Fits comfortably | ~63 tok/sEstimated | 37GB (have 80GB) |
| AI Mo Kimina Prover 72B | 72B | Q8 | Fits comfortably | ~44 tok/sEstimated | 73GB (have 80GB) |
| AI Mo Kimina Prover 72B | 72B | FP16 | Not supported | ~24 tok/sEstimated | 146GB (have 80GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | Q4 | Fits comfortably | ~375 tok/sEstimated | 1GB (have 80GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | Q8 | Fits comfortably | ~265 tok/sEstimated | 2GB (have 80GB) |
| Alibaba Nlp Gte Qwen2 1.5B Instruct | 1.5B | FP16 | Fits comfortably | ~145 tok/sEstimated | 4GB (have 80GB) |
Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data
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.