Can the Apple M2 (8 GB) run Kolors?

64 pts

Yes, with little memory to spare

Tight fit. At FP8 it needs about 4.8 GB of 5.4 GB usable, with an estimated speed of 75 s.

Best precision: FP8
Memory mode: Text encoder offloaded
Time per image: 75 s
Output: 1024×1024, 25 steps

Download Kolors

Original weights · Hugging Face

Full-precision files from Kuaishou, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/Kwai-Kolors/Kolors-diffusers (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/Kwai-Kolors/Kolors (opens in a new tab)

git clone https://github.com/Kwai-Kolors/Kolors

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.	26.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	18.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.5 / 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	64.9 / 100	64 ptsGood (B) · 64 of 100 points: Model quality 26.5/45, Memory fit 18.0/25, Speed 5.5/15, Memory use 15.0/15

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

Every precision on the Apple M2 (8 GB)

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	3.8 GB	5.4 GB	1.7 min	Sequential CPU offload	Runs well	58 ptsGood (B) · 58 of 100 points: Model quality 27.0/45, Memory fit 12.0/25, Speed 4.7/15, Memory use 15.0/15	Original weights (opens in a new tab)
`FP8`	4.8 GB	5.4 GB	75 s	Text encoder offloaded	Tight fit	64 ptsGood (B) · 64 of 100 points: Model quality 26.5/45, Memory fit 18.0/25, Speed 5.5/15, Memory use 15.0/15	Original weights (opens in a new tab)

Other hardware that runs it

82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX FP16 · 4.5 s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 FP16 · 7.5 s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 FP16 · 4.0 s
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT FP8 · 4.8 s
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB FP8 · 9.7 s
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER FP8 · 5.8 s

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.