Check my GPU

on

Can the Apple M4 Pro (48 GB) run Kimi Linear 48B-A3B?

85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q4_K_M it needs about 33.5 GB of 36.0 GB usable, with an estimated speed of 48.1 tok/s.

Best quant
Q4_K_M
Generation speed
48.1 tok/s
Prompt processing
1,901 tok/s
First token (1K prompt)
0.5 s
Largest safe context
309K

Download Kimi Linear 48B-A3B

Recommended for the Apple M4 Pro (48 GB): Q4_K_M. 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 Q4_K_M file (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:Q4_K_M

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.31.6 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 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.15.0 / 15
Total85.6 / 10085 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

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

Every quantization on the Apple M4 Pro (48 GB)

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 23.2 GB 36.0 GB 79.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15 GGUF (opens in a new tab)
Q3_K_M 27.6 GB 36.0 GB 62.2 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q4_K_M 33.5 GB 36.0 GB 48.1 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 38.4 GB 36.0 GB 33.8 tok/s Runs with offload 71 ptsGood (B) · 71 of 100 points: Model quality 32.3/45, Memory fit 10.0/25, Speed 13.8/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 43.8 GB 36.0 GB 28.4 tok/s Heavy offload 64 ptsGood (B) · 64 of 100 points: Model quality 33.0/45, Memory fit 4.0/25, Speed 12.6/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 55.6 GB 36.0 GB — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF · folder (opens in a new tab)
F16 102 GB 36.0 GB — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 10.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 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.