Check my GPU

on

Can the NVIDIA RTX PRO 6000 Blackwell run Kimi Linear 48B-A3B?

87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15

Yes, it runs well

Runs well. At Q8_0 it needs about 57.5 GB of 96.0 GB usable, with an estimated speed of 187 tok/s.

Best quant
Q8_0
Generation speed
187 tok/s
Prompt processing
30,000 tok/s
First token (1K prompt)
0.3 s
Largest safe context
1,024K

Download Kimi Linear 48B-A3B

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q8_0. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q8_0 files (opens in a new tab)

huggingface.co/bartowski/moonshotai_Kimi-Linear-48B-A3B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/moonshotai_Kimi-Linear-48B-A3B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Moonshot AI. The weights themselves download from Hugging Face.

github.com/MoonshotAI/Kimi-Linear (opens in a new tab)

git clone https://github.com/MoonshotAI/Kimi-Linear

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

How the S 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.33.3 / 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.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.13.8 / 15
Total87.1 / 10087 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15

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 25.1 GB 96.0 GB 602 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 23.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 GGUF (opens in a new tab)
Q3_K_M 29.5 GB 96.0 GB 474 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15 GGUF (opens in a new tab)
Q4_K_M 35.4 GB 96.0 GB 367 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15 GGUF (opens in a new tab)
Q5_K_M 40.3 GB 96.0 GB 303 tok/s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.7/15 GGUF (opens in a new tab)
Q6_K 45.7 GB 96.0 GB 254 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15 GGUF (opens in a new tab)
Q8_0 57.5 GB 96.0 GB 187 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15 GGUF · folder (opens in a new tab)
F16 104 GB 96.0 GB 28.4 tok/s Runs with offload 70 ptsGood (B) · 70 of 100 points: Model quality 33.3/45, Memory fit 10.0/25, Speed 12.6/15, Memory use 15.0/15 GGUF · folder (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.