Check my GPU

on

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

63 ptsGood (B) · 63 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 12.1/15

Yes, it runs well

Runs well. At Q4_K_M it needs about 11.3 GB of 21.4 GB usable, with an estimated speed of 24.8 tok/s.

Best quant
Q4_K_M
Generation speed
24.8 tok/s
Prompt processing
494 tok/s
First token (1K prompt)
2.1 s
Largest safe context
8K

Download CodeGemma 7B

Recommended for the Apple M2 Pro (32 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run codegemma:7b-instruct-q4_K_M

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

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

Download the Q4_K_M file (opens in a new tab)

huggingface.co/lmstudio-community/codegemma-7b-it-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/codegemma-7b-it-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/google/codegemma-7b-it (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Google approves it (usually within minutes to a few hours).

Official repo · GitHub

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

github.com/google-deepmind/gemma (opens in a new tab)

git clone https://github.com/google-deepmind/gemma

Google DeepMind’s official Gemma library.

Links checked 1 week 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.14.5 / 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.11.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.12.1 / 15
Total63.5 / 10063 ptsGood (B) · 63 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 12.1/15

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 9.5 GB 21.4 GB 40.7 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 10.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 GGUF (opens in a new tab)
Q3_K_M 10.3 GB 21.4 GB 32.0 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 11.0/15 GGUF (opens in a new tab)
Q4_K_M 11.3 GB 21.4 GB 24.8 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 12.1/15 GGUF (opens in a new tab)
Q5_K_M 12.1 GB 21.4 GB 20.5 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 14.8/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 13.1/15 GGUF (opens in a new tab)
Q6_K 13.1 GB 21.4 GB 17.2 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 14.1/15 GGUF (opens in a new tab)
Q8_0 15.1 GB 21.4 GB 12.6 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 8.4/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 23.2 GB 21.4 GB 4.9 tok/s Runs with offload 45 ptsUsable (C) · 45 of 100 points: Model quality 15.3/45, Memory fit 10.0/25, Speed 5.3/15, Memory use 15.0/15 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.