Check my GPU

LLMs ·

Kimi Linear 48B-A3B

Parameters
49B (3.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
mit
Released
2025-10

How to run it

Quantized files · GGUF

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

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 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: hybrid linear attention: about 1 in 4 layers keeps a latent (MLA) cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 19.6 GB 20.3 GB 20.5 GB GGUF (opens in a new tab)
Q3_K_M Low 24.1 GB 24.7 GB 24.9 GB GGUF (opens in a new tab)
Q4_K_M Good 30.0 GB 30.6 GB 30.8 GB GGUF (opens in a new tab)
Q5_K_M High 34.9 GB 35.5 GB 35.7 GB GGUF (opens in a new tab)
Q6_K High 40.3 GB 40.9 GB 41.1 GB GGUF (opens in a new tab)
Q8_0 Very high 52.1 GB 52.7 GB 52.9 GB GGUF · folder (opens in a new tab)
F16 Full 98.2 GB 98.9 GB 99.1 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Kimi Linear 48B-A3B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at Q3_K_M.

Grade · points Hardware Quant Memory Speed Fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.5/15 Apple M4 Max (128 GB) Q8_0 60.4 GB / 96.0 GB 49.0 tok/s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q5_K_M 39.4 GB / 48.0 GB 58.2 tok/s Runs well
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q5_K_M 39.4 GB / 48.0 GB 79.5 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 NVIDIA RTX PRO 6000 Blackwell Q8_0 57.5 GB / 96.0 GB 187 tok/s Runs well
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 Apple M4 Pro (48 GB) Q4_K_M 33.5 GB / 36.0 GB 48.1 tok/s Tight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15 Apple M2 Ultra (192 GB) Q8_0 64.3 GB / 144 GB 71.7 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 NVIDIA GeForce RTX 5090 Q3_K_M 26.3 GB / 32.0 GB 474 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 33.0/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 10.0/15 NVIDIA GB10 (128 GB) Q6_K 50.2 GB / 115 GB 38.8 tok/s Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 32.3/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 10.4/15 AMD Ryzen AI Max+ 395 (128 GB) Q5_K_M 43.2 GB / 96.0 GB 37.3 tok/s Runs well
81 ptsGreat (A) · 81 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 Apple M3 Ultra (256 GB) Q8_0 68.1 GB / 192 GB 73.5 tok/s Runs well

Check it on your own hardware

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.