Check my GPU

on

Can the NVIDIA RTX PRO 6000 Blackwell run Qwen2 72B Instruct?

78 ptsGreat (A) · 78 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 12.6/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 52.4 GB of 96.0 GB usable, with an estimated speed of 30.3 tok/s.

Best quant
Q4_K_M
Generation speed
30.3 tok/s
Prompt processing
1,238 tok/s
First token (1K prompt)
0.8 s
Largest safe context
32K

Download Qwen2 72B Instruct

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run qwen2:72b-instruct-q4_K_M

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/Qwen/Qwen2-72B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/Qwen/Qwen2-72B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen2-72B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.27.4 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.13.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.12.6 / 15
Total78.0 / 10078 ptsGreat (A) · 78 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 12.6/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA RTX PRO 6000 Blackwell

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 37.2 GB 96.0 GB 49.7 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 20.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15 GGUF (opens in a new tab)
Q3_K_M 43.7 GB 96.0 GB 39.1 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 24.2/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 10.5/15 GGUF (opens in a new tab)
Q4_K_M 52.4 GB 96.0 GB 30.3 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 12.6/15 GGUF (opens in a new tab)
Q5_K_M 59.7 GB 96.0 GB 25.0 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 14.4/15 GGUF · part 1 of 2 (opens in a new tab)
Q6_K 67.7 GB 96.0 GB 21.0 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 15.0/15 GGUF · part 1 of 2 (opens in a new tab)
Q8_0 85.2 GB 96.0 GB 15.4 tok/s Tight fit 77 ptsGreat (A) · 77 of 100 points: Model quality 28.8/45, Memory fit 24.0/25, Speed 9.3/15, Memory use 15.0/15 GGUF · part 1 of 2 (opens in a new tab)
F16 154 GB 96.0 GB — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · part 1 of 4 (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.