Can the Apple M2 Pro (32 GB) run InternLM 7B?

51 pts

Yes, it runs well

Runs well. At Q3_K_M it needs about 7.0 GB of 21.4 GB usable, with an estimated speed of 37.3 tok/s.

Best quant: Q3_K_M
Generation speed: 37.3 tok/s
Prompt processing: 576 tok/s
First token (1K prompt): 1.8 s
Largest safe context: 2K

Download InternLM 7B

Original weights · Hugging Face

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

huggingface.co/internlm/internlm-7b (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the C 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.	4.5 / 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.	14.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.5 / 15
Total	51.5 / 100	51 ptsUsable (C) · 51 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 7.5/15

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

Every quantization on the Apple M2 Pro (32 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	6.3 GB	21.4 GB	47.4 tok/s	Runs well	50 ptsUsable (C) · 50 of 100 points: Model quality 3.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15	All files (opens in a new tab)
`Q3_K_M`	7.0 GB	21.4 GB	37.3 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 7.5/15	All files (opens in a new tab)
`Q4_K_M`	7.9 GB	21.4 GB	28.9 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 5.1/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.5/15	All files (opens in a new tab)
`Q5_K_M`	8.6 GB	21.4 GB	23.9 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 5.2/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.2/15	All files (opens in a new tab)
`Q6_K`	9.4 GB	21.4 GB	20.0 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 10.1/15	All files (opens in a new tab)
`Q8_0`	11.1 GB	21.4 GB	14.7 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 9.1/15, Memory use 12.0/15	All files (opens in a new tab)
`F16`	18.0 GB	21.4 GB	6.8 tok/s	Runs well	51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 15.0/15	Original weights (opens in a new tab)

Memory figures assume 2K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

60 ptsGood (B) · 60 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 SUPER Q8_0 · 43.0 tok/s
60 ptsGood (B) · 60 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Intel Arc B580 Q6_K · 40.5 tok/s
60 ptsGood (B) · 60 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3060 12GB Q6_K · 41.9 tok/s
60 ptsGood (B) · 60 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 AMD Radeon RX 9070 XT Q8_0 · 47.0 tok/s
60 ptsGood (B) · 60 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 57.4 tok/s
60 ptsGood (B) · 60 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15 NVIDIA GeForce RTX 4080 SUPER Q8_0 · 62.8 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.