Can the Apple M2 (8 GB) run Codestral Mamba 7B?

62 pts

Yes, it runs well

Runs well. At Q2_K it needs about 4.0 GB of 5.4 GB usable, with an estimated speed of 23.8 tok/s.

Best quant: Q2_K
Generation speed: 23.8 tok/s
Prompt processing: 306 tok/s
First token (1K prompt): 3.3 s
Largest safe context: 256K

Download Codestral Mamba 7B

Original weights · Hugging Face

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

huggingface.co/mistralai/Mamba-Codestral-7B-v0.1 (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.	11.3 / 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.	11.6 / 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	62.9 / 100	62 ptsGood (B) · 62 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 11.6/15, 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 M2 (8 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	4.0 GB	5.4 GB	23.8 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 15.0/15	All files (opens in a new tab)
`Q3_K_M`	4.6 GB	5.4 GB	18.7 tok/s	Tight fit	62 ptsGood (B) · 62 of 100 points: Model quality 13.6/45, Memory fit 24.0/25, Speed 10.3/15, Memory use 15.0/15	All files (opens in a new tab)
`Q4_K_M`	5.5 GB	5.4 GB	12.3 tok/s	Runs with offload	48 ptsUsable (C) · 48 of 100 points: Model quality 15.4/45, Memory fit 10.0/25, Speed 8.3/15, Memory use 15.0/15	All files (opens in a new tab)
`Q5_K_M`	6.2 GB	5.4 GB	10.2 tok/s	Heavy offload	42 ptsUsable (C) · 42 of 100 points: Model quality 15.7/45, Memory fit 4.0/25, Speed 7.6/15, Memory use 15.0/15	All files (opens in a new tab)
`Q6_K`	7.0 GB	5.4 GB	—	Won't run	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	All files (opens in a new tab)
`Q8_0`	8.8 GB	5.4 GB	—	Won't run	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	All files (opens in a new tab)
`F16`	15.6 GB	5.4 GB	—	Won't run	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.9/45, 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

71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.2 tok/s
70 ptsGood (B) · 70 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Q4_K_M · 45.8 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15 Intel Arc B580 Q6_K · 40.7 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15 NVIDIA GeForce RTX 3060 12GB Q6_K · 42.1 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15 AMD Radeon RX 9070 XT Q8_0 · 47.2 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 57.6 tok/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.