L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsOpenClawMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Guides

  • OpenClaw Guide
  • How-To Guides

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

  1. Home
  2. GPUs
  3. Apple M4 Max

Quick Answer: Apple M4 Max offers 128GB VRAM and starts around current market pricing. It delivers approximately 98 tokens/sec on deepseek-ai/DeepSeek-OCR. It typically draws 45W under load.

Apple M4 Max

Unknown
By AppleReleased 2024-11MSRP $3,999.00

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.

Check Price on AmazonView Benchmarks
Specs snapshot
Key hardware metrics for AI workloads.
VRAM128GB
Cores40
TDP45W
ArchitectureApple Silicon M4
Key Takeaways
  • 128GB VRAM - runs models up to ~320B parameters
  • Very efficient (45W) - suitable for compact builds
  • Strong price-to-VRAM value

What this means for you

With 128GB VRAM, Apple M4 Max can run models up to approximately 320B parameters using 4-bit quantization. This handles most popular models including Llama 3 70B, Mistral 7B, and larger.

Who should buy

  • Professional AI workloads requiring maximum VRAM
  • Running 100B+ parameter models with full precision

Looking to upgrade?

Consider H100 or MI300X — Maximum VRAM for enterprise workloads.

Where to Buy

Buy directly on Amazon with fast shipping and reliable customer service.

💰Price Analysis
Good price range.
Current Price
Apple M4 Max
$499
Buy on Amazon
+4.4% over 30 days
30-day low
$462
30-day avg
$502
30-day high
$540
Get email when price drops
AmazonUnknown
See price on Amazon
Check availability
Buy on Amazon

Prime shipping available • 30-day returns

More Amazon options

Rotate out primary variants whenever validation flags an issue.

Complete Your Build

Essential accessories to pair with Apple M4 Max

Corsair RM750x (2025) 750W
Minimum 750W recommended for RTX 40 series
$119
Find on Amazon
Corsair Vengeance 32GB DDR5-6000
32GB ideal for AI workloads
$129
Find on Amazon
Noctua NF-A12x25 PWM
Quiet and efficient cooling
$35
Find on Amazon
Thermal Grizzly Kryonaut
Premium thermal paste for optimal cooling
$15
Find on Amazon

Total Bundle Price

All items from Amazon

$797
Individual: $797
Find All on AmazonMore GPUs

💡 Not ready to buy? Try cloud GPUs first

Test Apple M4 Max performance in the cloud before investing in hardware. Pay by the hour with no commitment.

Vast.aifrom $0.20/hrRunPodfrom $0.30/hrLambda Labsenterprise-grade

AI benchmarks

ModelQuantizationTokens/secVRAM used
deepseek-ai/DeepSeek-OCRQ4
98.27 tok/sEstimated

Auto-generated benchmark

2GB
Qwen/Qwen2.5-3B-InstructQ4
96.02 tok/sEstimated

Auto-generated benchmark

2GB
unsloth/Llama-3.2-1B-InstructQ4
95.43 tok/sEstimated

Auto-generated benchmark

1GB
Qwen/Qwen2.5-3BQ4
95.08 tok/sEstimated

Auto-generated benchmark

2GB
google/gemma-2-2b-itQ4
94.96 tok/sEstimated

Auto-generated benchmark

1GB
meta-llama/Llama-3.2-3B-InstructQ4
94.79 tok/sEstimated

Auto-generated benchmark

2GB
bigcode/starcoder2-3bQ4
93.98 tok/sEstimated

Auto-generated benchmark

2GB
google-t5/t5-3bQ4
92.03 tok/sEstimated

Auto-generated benchmark

2GB
tencent/HunyuanOCRQ4
91.77 tok/sEstimated

Auto-generated benchmark

1GB
ibm-granite/granite-3.3-2b-instructQ4
91.71 tok/sEstimated

Auto-generated benchmark

1GB
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4
91.63 tok/sEstimated

Auto-generated benchmark

1GB
apple/OpenELM-1_1B-InstructQ4
91.09 tok/sEstimated

Auto-generated benchmark

1GB
google/gemma-2bQ4
90.84 tok/sEstimated

Auto-generated benchmark

1GB
WeiboAI/VibeThinker-1.5BQ4
90.71 tok/sEstimated

Auto-generated benchmark

1GB
context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16Q4
90.37 tok/sEstimated

Auto-generated benchmark

2GB
inference-net/Schematron-3BQ4
90.35 tok/sEstimated

Auto-generated benchmark

2GB
unsloth/Llama-3.2-3B-InstructQ4
89.14 tok/sEstimated

Auto-generated benchmark

2GB
unsloth/gemma-3-1b-itQ4
89.08 tok/sEstimated

Auto-generated benchmark

1GB
meta-llama/Llama-3.2-3BQ4
87.90 tok/sEstimated

Auto-generated benchmark

2GB
google/embeddinggemma-300mQ4
87.40 tok/sEstimated

Auto-generated benchmark

1GB
facebook/sam3Q4
87.37 tok/sEstimated

Auto-generated benchmark

1GB
google-bert/bert-base-uncasedQ4
86.75 tok/sEstimated

Auto-generated benchmark

1GB
nineninesix/kani-tts-2-enQ4
86.43 tok/sEstimated

Auto-generated benchmark

1GB
deepseek-ai/DeepSeek-OCR-2Q4
86.32 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-3.2-1B-InstructQ4
85.28 tok/sEstimated

Auto-generated benchmark

1GB
google/gemma-3-1b-itQ4
85.19 tok/sEstimated

Auto-generated benchmark

1GB
deepseek-ai/deepseek-coder-1.3b-instructQ4
84.80 tok/sEstimated

Auto-generated benchmark

2GB
allenai/OLMo-2-0425-1BQ4
84.76 tok/sEstimated

Auto-generated benchmark

1GB
Qwen/Qwen3-ASR-1.7BQ4
84.11 tok/sEstimated

Auto-generated benchmark

2GB
nari-labs/Dia2-2BQ4
83.51 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-3.2-1BQ4
83.21 tok/sEstimated

Auto-generated benchmark

1GB
ibm-research/PowerMoE-3bQ4
82.90 tok/sEstimated

Auto-generated benchmark

2GB
meta-llama/Llama-Guard-3-1BQ4
80.80 tok/sEstimated

Auto-generated benchmark

1GB
numind/NuExtract-1.5Q4
80.43 tok/sEstimated

Auto-generated benchmark

4GB
deepseek-ai/DeepSeek-V3-0324Q4
80.31 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen3-8B-BaseQ4
80.19 tok/sEstimated

Auto-generated benchmark

4GB
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bitQ4
80.09 tok/sEstimated

Auto-generated benchmark

2GB
moonshotai/Kimi-K2.5Q4
80.08 tok/sEstimated

Auto-generated benchmark

4GB
unsloth/Meta-Llama-3.1-8B-InstructQ4
79.94 tok/sEstimated

Auto-generated benchmark

4GB
microsoft/phi-4Q4
79.91 tok/sEstimated

Auto-generated benchmark

4GB
trl-internal-testing/tiny-random-LlamaForCausalLMQ4
79.79 tok/sEstimated

Auto-generated benchmark

4GB
black-forest-labs/FLUX.2-devQ4
79.75 tok/sEstimated

Auto-generated benchmark

4GB
Qwen/Qwen2.5-Math-1.5BQ4
79.65 tok/sEstimated

Auto-generated benchmark

3GB
deepseek-ai/DeepSeek-V3Q4
79.34 tok/sEstimated

Auto-generated benchmark

4GB
openai-community/gpt2-mediumQ4
79.32 tok/sEstimated

Auto-generated benchmark

4GB
liuhaotian/llava-v1.5-7bQ4
79.30 tok/sEstimated

Auto-generated benchmark

4GB
LiquidAI/LFM2-1.2BQ4
79.30 tok/sEstimated

Auto-generated benchmark

1GB
vikhyatk/moondream2Q4
79.28 tok/sEstimated

Auto-generated benchmark

4GB
ibm-granite/granite-docling-258MQ4
79.25 tok/sEstimated

Auto-generated benchmark

4GB
microsoft/Phi-3.5-mini-instructQ4
78.70 tok/sEstimated

Auto-generated benchmark

2GB
deepseek-ai/DeepSeek-OCR
Q4
2GB
98.27 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B-Instruct
Q4
2GB
96.02 tok/sEstimated
Auto-generated benchmark
unsloth/Llama-3.2-1B-Instruct
Q4
1GB
95.43 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-3B
Q4
2GB
95.08 tok/sEstimated
Auto-generated benchmark
google/gemma-2-2b-it
Q4
1GB
94.96 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B-Instruct
Q4
2GB
94.79 tok/sEstimated
Auto-generated benchmark
bigcode/starcoder2-3b
Q4
2GB
93.98 tok/sEstimated
Auto-generated benchmark
google-t5/t5-3b
Q4
2GB
92.03 tok/sEstimated
Auto-generated benchmark
tencent/HunyuanOCR
Q4
1GB
91.77 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-3.3-2b-instruct
Q4
1GB
91.71 tok/sEstimated
Auto-generated benchmark
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Q4
1GB
91.63 tok/sEstimated
Auto-generated benchmark
apple/OpenELM-1_1B-Instruct
Q4
1GB
91.09 tok/sEstimated
Auto-generated benchmark
google/gemma-2b
Q4
1GB
90.84 tok/sEstimated
Auto-generated benchmark
WeiboAI/VibeThinker-1.5B
Q4
1GB
90.71 tok/sEstimated
Auto-generated benchmark
context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16
Q4
2GB
90.37 tok/sEstimated
Auto-generated benchmark
inference-net/Schematron-3B
Q4
2GB
90.35 tok/sEstimated
Auto-generated benchmark
unsloth/Llama-3.2-3B-Instruct
Q4
2GB
89.14 tok/sEstimated
Auto-generated benchmark
unsloth/gemma-3-1b-it
Q4
1GB
89.08 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-3B
Q4
2GB
87.90 tok/sEstimated
Auto-generated benchmark
google/embeddinggemma-300m
Q4
1GB
87.40 tok/sEstimated
Auto-generated benchmark
facebook/sam3
Q4
1GB
87.37 tok/sEstimated
Auto-generated benchmark
google-bert/bert-base-uncased
Q4
1GB
86.75 tok/sEstimated
Auto-generated benchmark
nineninesix/kani-tts-2-en
Q4
1GB
86.43 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-OCR-2
Q4
2GB
86.32 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B-Instruct
Q4
1GB
85.28 tok/sEstimated
Auto-generated benchmark
google/gemma-3-1b-it
Q4
1GB
85.19 tok/sEstimated
Auto-generated benchmark
deepseek-ai/deepseek-coder-1.3b-instruct
Q4
2GB
84.80 tok/sEstimated
Auto-generated benchmark
allenai/OLMo-2-0425-1B
Q4
1GB
84.76 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-ASR-1.7B
Q4
2GB
84.11 tok/sEstimated
Auto-generated benchmark
nari-labs/Dia2-2B
Q4
2GB
83.51 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-3.2-1B
Q4
1GB
83.21 tok/sEstimated
Auto-generated benchmark
ibm-research/PowerMoE-3b
Q4
2GB
82.90 tok/sEstimated
Auto-generated benchmark
meta-llama/Llama-Guard-3-1B
Q4
1GB
80.80 tok/sEstimated
Auto-generated benchmark
numind/NuExtract-1.5
Q4
4GB
80.43 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-V3-0324
Q4
4GB
80.31 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen3-8B-Base
Q4
4GB
80.19 tok/sEstimated
Auto-generated benchmark
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bit
Q4
2GB
80.09 tok/sEstimated
Auto-generated benchmark
moonshotai/Kimi-K2.5
Q4
4GB
80.08 tok/sEstimated
Auto-generated benchmark
unsloth/Meta-Llama-3.1-8B-Instruct
Q4
4GB
79.94 tok/sEstimated
Auto-generated benchmark
microsoft/phi-4
Q4
4GB
79.91 tok/sEstimated
Auto-generated benchmark
trl-internal-testing/tiny-random-LlamaForCausalLM
Q4
4GB
79.79 tok/sEstimated
Auto-generated benchmark
black-forest-labs/FLUX.2-dev
Q4
4GB
79.75 tok/sEstimated
Auto-generated benchmark
Qwen/Qwen2.5-Math-1.5B
Q4
3GB
79.65 tok/sEstimated
Auto-generated benchmark
deepseek-ai/DeepSeek-V3
Q4
4GB
79.34 tok/sEstimated
Auto-generated benchmark
openai-community/gpt2-medium
Q4
4GB
79.32 tok/sEstimated
Auto-generated benchmark
liuhaotian/llava-v1.5-7b
Q4
4GB
79.30 tok/sEstimated
Auto-generated benchmark
LiquidAI/LFM2-1.2B
Q4
1GB
79.30 tok/sEstimated
Auto-generated benchmark
vikhyatk/moondream2
Q4
4GB
79.28 tok/sEstimated
Auto-generated benchmark
ibm-granite/granite-docling-258M
Q4
4GB
79.25 tok/sEstimated
Auto-generated benchmark
microsoft/Phi-3.5-mini-instruct
Q4
2GB
78.70 tok/sEstimated
Auto-generated benchmark

Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data

Model compatibility

ModelQuantizationVerdictEstimated speedVRAM needed
openai-community/gpt2Q8Fits comfortably
52.62 tok/sEstimated
7GB (have 128GB)
openai-community/gpt2FP16Fits comfortably
25.71 tok/sEstimated
15GB (have 128GB)
Qwen/Qwen2.5-7B-InstructQ4Fits comfortably
71.21 tok/sEstimated
4GB (have 128GB)
Qwen/Qwen2.5-7B-InstructQ8Fits comfortably
47.46 tok/sEstimated
7GB (have 128GB)
Qwen/Qwen2.5-7B-InstructFP16Fits comfortably
30.30 tok/sEstimated
15GB (have 128GB)
Qwen/Qwen3-0.6BQ4Fits comfortably
75.71 tok/sEstimated
3GB (have 128GB)
Qwen/Qwen3-0.6BQ8Fits comfortably
53.46 tok/sEstimated
6GB (have 128GB)
Qwen/Qwen3-0.6BFP16Fits comfortably
30.31 tok/sEstimated
13GB (have 128GB)
Gensyn/Qwen2.5-0.5B-InstructQ4Fits comfortably
70.95 tok/sEstimated
3GB (have 128GB)
Gensyn/Qwen2.5-0.5B-InstructQ8Fits comfortably
46.66 tok/sEstimated
5GB (have 128GB)
Gensyn/Qwen2.5-0.5B-InstructFP16Fits comfortably
29.91 tok/sEstimated
11GB (have 128GB)
meta-llama/Llama-3.1-8B-InstructQ4Fits comfortably
77.72 tok/sEstimated
4GB (have 128GB)
meta-llama/Llama-3.1-8B-InstructQ8Fits comfortably
46.69 tok/sEstimated
9GB (have 128GB)
meta-llama/Llama-3.1-8B-InstructFP16Fits comfortably
29.75 tok/sEstimated
17GB (have 128GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ4Fits comfortably
26.73 tok/sEstimated
17GB (have 128GB)
dphn/dolphin-2.9.1-yi-1.5-34bQ8Fits comfortably
19.42 tok/sEstimated
35GB (have 128GB)
dphn/dolphin-2.9.1-yi-1.5-34bFP16Fits comfortably
9.15 tok/sEstimated
70GB (have 128GB)
openai/gpt-oss-20bQ4Fits comfortably
38.62 tok/sEstimated
10GB (have 128GB)
openai/gpt-oss-20bQ8Fits comfortably
29.66 tok/sEstimated
20GB (have 128GB)
openai/gpt-oss-20bFP16Fits comfortably
13.78 tok/sEstimated
41GB (have 128GB)
google/gemma-3-1b-itQ4Fits comfortably
85.19 tok/sEstimated
1GB (have 128GB)
google/gemma-3-1b-itQ8Fits comfortably
60.47 tok/sEstimated
1GB (have 128GB)
google/gemma-3-1b-itFP16Fits comfortably
36.34 tok/sEstimated
2GB (have 128GB)
Qwen/Qwen3-Embedding-0.6BQ4Fits comfortably
70.69 tok/sEstimated
3GB (have 128GB)
Qwen/Qwen3-Embedding-0.6BQ8Fits comfortably
51.87 tok/sEstimated
6GB (have 128GB)
Qwen/Qwen3-Embedding-0.6BFP16Fits comfortably
30.43 tok/sEstimated
13GB (have 128GB)
Qwen/Qwen2.5-1.5B-InstructQ4Fits comfortably
70.92 tok/sEstimated
3GB (have 128GB)
Qwen/Qwen2.5-1.5B-InstructQ8Fits comfortably
53.03 tok/sEstimated
5GB (have 128GB)
Qwen/Qwen2.5-1.5B-InstructFP16Fits comfortably
28.53 tok/sEstimated
11GB (have 128GB)
facebook/opt-125mQ4Fits comfortably
76.39 tok/sEstimated
4GB (have 128GB)
facebook/opt-125mQ8Fits comfortably
46.39 tok/sEstimated
7GB (have 128GB)
facebook/opt-125mFP16Fits comfortably
27.10 tok/sEstimated
15GB (have 128GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4Fits comfortably
91.63 tok/sEstimated
1GB (have 128GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8Fits comfortably
56.56 tok/sEstimated
1GB (have 128GB)
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16Fits comfortably
34.15 tok/sEstimated
2GB (have 128GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4Fits comfortably
70.12 tok/sEstimated
4GB (have 128GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8Fits comfortably
52.70 tok/sEstimated
7GB (have 128GB)
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16Fits comfortably
25.71 tok/sEstimated
15GB (have 128GB)
Qwen/Qwen3-4B-Instruct-2507Q4Fits comfortably
74.29 tok/sEstimated
2GB (have 128GB)
Qwen/Qwen3-4B-Instruct-2507Q8Fits comfortably
46.57 tok/sEstimated
4GB (have 128GB)
Qwen/Qwen3-4B-Instruct-2507FP16Fits comfortably
26.97 tok/sEstimated
9GB (have 128GB)
meta-llama/Llama-3.2-1B-InstructQ4Fits comfortably
85.28 tok/sEstimated
1GB (have 128GB)
meta-llama/Llama-3.2-1B-InstructQ8Fits comfortably
61.91 tok/sEstimated
1GB (have 128GB)
meta-llama/Llama-3.2-1B-InstructFP16Fits comfortably
34.90 tok/sEstimated
2GB (have 128GB)
openai/gpt-oss-120bQ4Fits comfortably
15.79 tok/sEstimated
59GB (have 128GB)
openai/gpt-oss-120bQ8Fits comfortably
9.42 tok/sEstimated
117GB (have 128GB)
openai/gpt-oss-120bFP16Not supported
5.33 tok/sEstimated
235GB (have 128GB)
Qwen/Qwen2.5-3B-InstructQ4Fits comfortably
96.02 tok/sEstimated
2GB (have 128GB)
Qwen/Qwen2.5-3B-InstructQ8Fits comfortably
58.91 tok/sEstimated
3GB (have 128GB)
openai-community/gpt2Q4Fits comfortably
77.53 tok/sEstimated
4GB (have 128GB)
openai-community/gpt2Q8
Fits comfortably7GB required · 128GB available
52.62 tok/sEstimated
openai-community/gpt2FP16
Fits comfortably15GB required · 128GB available
25.71 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ4
Fits comfortably4GB required · 128GB available
71.21 tok/sEstimated
Qwen/Qwen2.5-7B-InstructQ8
Fits comfortably7GB required · 128GB available
47.46 tok/sEstimated
Qwen/Qwen2.5-7B-InstructFP16
Fits comfortably15GB required · 128GB available
30.30 tok/sEstimated
Qwen/Qwen3-0.6BQ4
Fits comfortably3GB required · 128GB available
75.71 tok/sEstimated
Qwen/Qwen3-0.6BQ8
Fits comfortably6GB required · 128GB available
53.46 tok/sEstimated
Qwen/Qwen3-0.6BFP16
Fits comfortably13GB required · 128GB available
30.31 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ4
Fits comfortably3GB required · 128GB available
70.95 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructQ8
Fits comfortably5GB required · 128GB available
46.66 tok/sEstimated
Gensyn/Qwen2.5-0.5B-InstructFP16
Fits comfortably11GB required · 128GB available
29.91 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ4
Fits comfortably4GB required · 128GB available
77.72 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructQ8
Fits comfortably9GB required · 128GB available
46.69 tok/sEstimated
meta-llama/Llama-3.1-8B-InstructFP16
Fits comfortably17GB required · 128GB available
29.75 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ4
Fits comfortably17GB required · 128GB available
26.73 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bQ8
Fits comfortably35GB required · 128GB available
19.42 tok/sEstimated
dphn/dolphin-2.9.1-yi-1.5-34bFP16
Fits comfortably70GB required · 128GB available
9.15 tok/sEstimated
openai/gpt-oss-20bQ4
Fits comfortably10GB required · 128GB available
38.62 tok/sEstimated
openai/gpt-oss-20bQ8
Fits comfortably20GB required · 128GB available
29.66 tok/sEstimated
openai/gpt-oss-20bFP16
Fits comfortably41GB required · 128GB available
13.78 tok/sEstimated
google/gemma-3-1b-itQ4
Fits comfortably1GB required · 128GB available
85.19 tok/sEstimated
google/gemma-3-1b-itQ8
Fits comfortably1GB required · 128GB available
60.47 tok/sEstimated
google/gemma-3-1b-itFP16
Fits comfortably2GB required · 128GB available
36.34 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ4
Fits comfortably3GB required · 128GB available
70.69 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BQ8
Fits comfortably6GB required · 128GB available
51.87 tok/sEstimated
Qwen/Qwen3-Embedding-0.6BFP16
Fits comfortably13GB required · 128GB available
30.43 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ4
Fits comfortably3GB required · 128GB available
70.92 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructQ8
Fits comfortably5GB required · 128GB available
53.03 tok/sEstimated
Qwen/Qwen2.5-1.5B-InstructFP16
Fits comfortably11GB required · 128GB available
28.53 tok/sEstimated
facebook/opt-125mQ4
Fits comfortably4GB required · 128GB available
76.39 tok/sEstimated
facebook/opt-125mQ8
Fits comfortably7GB required · 128GB available
46.39 tok/sEstimated
facebook/opt-125mFP16
Fits comfortably15GB required · 128GB available
27.10 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q4
Fits comfortably1GB required · 128GB available
91.63 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0Q8
Fits comfortably1GB required · 128GB available
56.56 tok/sEstimated
TinyLlama/TinyLlama-1.1B-Chat-v1.0FP16
Fits comfortably2GB required · 128GB available
34.15 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q4
Fits comfortably4GB required · 128GB available
70.12 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5Q8
Fits comfortably7GB required · 128GB available
52.70 tok/sEstimated
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5FP16
Fits comfortably15GB required · 128GB available
25.71 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q4
Fits comfortably2GB required · 128GB available
74.29 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507Q8
Fits comfortably4GB required · 128GB available
46.57 tok/sEstimated
Qwen/Qwen3-4B-Instruct-2507FP16
Fits comfortably9GB required · 128GB available
26.97 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ4
Fits comfortably1GB required · 128GB available
85.28 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructQ8
Fits comfortably1GB required · 128GB available
61.91 tok/sEstimated
meta-llama/Llama-3.2-1B-InstructFP16
Fits comfortably2GB required · 128GB available
34.90 tok/sEstimated
openai/gpt-oss-120bQ4
Fits comfortably59GB required · 128GB available
15.79 tok/sEstimated
openai/gpt-oss-120bQ8
Fits comfortably117GB required · 128GB available
9.42 tok/sEstimated
openai/gpt-oss-120bFP16
Not supported235GB required · 128GB available
5.33 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ4
Fits comfortably2GB required · 128GB available
96.02 tok/sEstimated
Qwen/Qwen2.5-3B-InstructQ8
Fits comfortably3GB required · 128GB available
58.91 tok/sEstimated
openai-community/gpt2Q4
Fits comfortably4GB required · 128GB available
77.53 tok/sEstimated

Note: Performance estimates are calculated. Real results may vary. Methodology · Submit real data

Alternative GPUs

RTX 5070
12GB

Explore how RTX 5070 stacks up for local inference workloads.

RTX 4060 Ti 16GB
16GB

Explore how RTX 4060 Ti 16GB stacks up for local inference workloads.

RX 6800 XT
16GB

Explore how RX 6800 XT stacks up for local inference workloads.

RTX 4070 Super
12GB

Explore how RTX 4070 Super stacks up for local inference workloads.

RTX 3080
10GB

Explore how RTX 3080 stacks up for local inference workloads.

Can it play popular games?

Cyberpunk 2077
8GB VRAM

RPG • 2020

Baldur's Gate 3
8GB VRAM

RPG • 2023

Hogwarts Legacy
12GB VRAM

Action RPG • 2023

Starfield
8GB VRAM

RPG • 2023

Alan Wake 2
12GB VRAM

Survival Horror • 2023

Elden Ring
8GB VRAM

Action RPG • 2022

Black Myth: Wukong
12GB VRAM

Action RPG • 2024

Grand Theft Auto VI
12GB VRAM

Action Adventure • 2025

Resident Evil 4 Remake
12GB VRAM

Survival Horror • 2023

Marvel's Spider-Man Remastered
12GB VRAM

Action • 2022

The Last of Us Part I
12GB VRAM

Action Adventure • 2023

Red Dead Redemption 2
8GB VRAM

Action Adventure • 2019

View all 64 compatible games