vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

M3 Max 64GB

Apple Silicon

64GB VRAM · 400 GB/s bandwidth · 32.8 FP16 TFLOPS · 75W TDP · $3,499 street price

The M3 Max 64GB has 64GB of VRAM with 400 GB/s memory bandwidth and 32.8 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (86 tok/s), Qwen 2.5 7B (45 tok/s), Llama 3.1 8B (42 tok/s). Models larger than ~109B parameters won't fit even at Q4. Electricity cost is approximately $8/month at 75W TDP.

What LLMs can you run?

ModelParamsQ4 WeightFitDecode
Gemma 3 4B4.0B2 GBcomfortable86 tok/s
Qwen 2.5 7B7.6B4 GBcomfortable45 tok/s
Llama 3.1 8B8.0B4 GBcomfortable42 tok/s
Mistral Small 24B24.0B12 GBtight14 tok/s
Gemma 3 27B27.4B14 GBtight12 tok/s
Qwen 2.5 Coder 32B32.5B16 GBtight10 tok/s
Llama 3.3 70B70.6B35 GBtight4 tok/s
Qwen 2.5 72B72.7B36 GBtight4 tok/s
Llama 3.1 405B405B202 GBwon't fit
DeepSeek R1 671B671B336 GBwon't fit

Similar GPUs

GPUVRAMBWTFLOPSTDP
M1 Max 64GB64GB400 GB/s21.260W
M2 Max 64GB64GB400 GB/s27.260W
Jetson T400064GB273 GB/s31.040W
M4 Max 64GB64GB546 GB/s36.975W
M1 Ultra 64GB64GB800 GB/s42.5120W

Compare with another GPU

Select another GPU to compare specs and model performance side by side.

Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0