Kimi K2.7 Code (1T) on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Kimi K2.7 Code (1T)?

59 pts

Barely: most of the model spills into system RAM

Heavy offload. At Q2_K it needs about 443 GB of 384 GB usable, with an estimated speed of 18.9 tok/s.

Best quant: Q2_K
Generation speed: 18.9 tok/s
Prompt processing: 550 tok/s
First token (1K prompt): 1.9 s
Largest safe context: —

Download Kimi K2.7 Code (1T)

Recommended for the Apple M3 Ultra (512 GB): Q2_K. 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 Q2_K (UD-Q2_K_XL) files (opens in a new tab)

huggingface.co/unsloth/Kimi-K2.7-Code-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF

Original weights · Hugging Face

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

huggingface.co/moonshotai/Kimi-K2.7-Code (opens in a new tab)

No sign-in needed.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

How the B 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.	29.7 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	10.3 / 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
Total	59.0 / 100	59 ptsGood (B) · 59 of 100 points: Model quality 29.7/45, Memory fit 4.0/25, Speed 10.3/15, 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 M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	443 GB	384 GB	18.9 tok/s	Heavy offload	59 ptsGood (B) · 59 of 100 points: Model quality 29.7/45, Memory fit 4.0/25, Speed 10.3/15, Memory use 15.0/15	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	535 GB	384 GB	—	Won't run	10 ptsWon't run (F) · 10 of 100 points: Model quality 10.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF · folder (opens in a new tab)
`Q4_K_M`	658 GB	384 GB	—	Won't run	12 ptsWon't run (F) · 12 of 100 points: Model quality 12.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
`Q5_K_M`	761 GB	384 GB	—	Won't run	12 ptsWon't run (F) · 12 of 100 points: Model quality 12.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF files (opens in a new tab)
`Q6_K`	874 GB	384 GB	—	Won't run	12 ptsWon't run (F) · 12 of 100 points: Model quality 12.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF files (opens in a new tab)
`Q8_0`	1,120 GB	384 GB	—	Won't run	12 ptsWon't run (F) · 12 of 100 points: Model quality 12.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (UD-Q8_K_XL) · folder (opens in a new tab)
`F16`	2,086 GB	384 GB	—	Won't run	12 ptsWon't run (F) · 12 of 100 points: Model quality 12.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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.