Code Llama 13B Instruct on Apple M2 Pro (32 GB)

Can the Apple M2 Pro (32 GB) run Code Llama 13B Instruct?

62 pts

Yes, it runs well

Runs well. At Q4_K_M it needs about 17.0 GB of 21.4 GB usable, with an estimated speed of 16.2 tok/s.

Best quant: Q4_K_M
Generation speed: 16.2 tok/s
Prompt processing: 324 tok/s
First token (1K prompt): 3.2 s
Largest safe context: 13K

Download Code Llama 13B Instruct

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 codellama:13b-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/TheBloke/CodeLlama-13B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/CodeLlama-13B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/meta-llama/CodeLlama-13b-Instruct-hf (opens in a new tab)

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

Official repo · GitHub

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

github.com/meta-llama/codellama (opens in a new tab)

git clone https://github.com/meta-llama/codellama

Meta’s official Code Llama repo.

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.	12.8 / 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.	9.6 / 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	62.4 / 100	62 ptsGood (B) · 62 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 9.6/15, 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 Pro (32 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	14.2 GB	21.4 GB	26.7 tok/s	Runs well	61 ptsGood (B) · 61 of 100 points: Model quality 9.5/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	15.4 GB	21.4 GB	21.0 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4_K_M`	17.0 GB	21.4 GB	16.2 tok/s	Runs well	62 ptsGood (B) · 62 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	18.3 GB	21.4 GB	13.4 tok/s	Tight fit	60 ptsGood (B) · 60 of 100 points: Model quality 13.1/45, Memory fit 24.0/25, Speed 8.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q6_K`	19.7 GB	21.4 GB	11.3 tok/s	Tight fit	60 ptsGood (B) · 60 of 100 points: Model quality 13.4/45, Memory fit 24.0/25, Speed 8.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	22.8 GB	21.4 GB	7.0 tok/s	Runs with offload	44 ptsUsable (C) · 44 of 100 points: Model quality 13.5/45, Memory fit 10.0/25, Speed 6.3/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	35.1 GB	21.4 GB	—	Won't run	4 ptsWon't run (F) · 4 of 100 points: Model quality 4.1/45, 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

68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q8_0 · 86.0 tok/s
68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q6_K · 54.1 tok/s
68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q6_K · 61.2 tok/s
68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q6_K · 65.9 tok/s
65 ptsGood (B) · 65 of 100 points: Model quality 11.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT Q3_K_M · 67.2 tok/s
65 ptsGood (B) · 65 of 100 points: Model quality 11.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q3_K_M · 81.9 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.