Skip to content

CodeLlama 7B HF on Mac mini M4 Pro 48 GB: VRAM, speed and fit

CodeLlama 7B HF at 8-bit runs on the M4 Pro 48 GB with 16K of context at about 29 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 Pro 48 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
27.1 GB
of 48.0 GB
Context
16K
auto
Speed
29 tok/s
14 when full
First reply
4.6 s
2K prompt

Where the memory goes

Model
6.7 GB
Context
8.0 GB
Overhead
447 MB
OS
12.0 GB
Free
20.9 GB
Memory
27.1 GB of 48.0 GB
Context
16K tokens · auto
Speed
29 tok/s · 14 when full
First reply
4.6 s for a 2K prompt
Running cost
$1.84/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated with conditions

What CodeLlama 7B HF on Mac mini M4 Pro 48 GB was checked against
CheckTargetResultStatus
Fits in GPU memory36.0 GB usable15.1 GB neededPass
Headroom5% free20.9 GB free (58%)Pass
Context for chat16K or more16KPass
Writing speed15 tok/s or more29 tok/sPass
First replyunder 3 s, 2K prompt4.6 sCheck

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
CodeLlama 7B HF
Parameters
6.7B
Precision
8-bit (Q8_0)
Context
16K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 Pro 48 GB
GPU can use
36.0 GB of 48.0 GB

Running cost

At home
$1.84/mo
84 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf TheBloke/CodeLlama-7B-GGUF
vLLM
vllm serve codellama/CodeLlama-7b-hf
MLX (Mac)
mlx_lm.chat --model mlx-community/CodeLlama-7b-hf-4bit-mlx

CodeLlama 7B HF on similar machines

All machines: CodeLlama 7B HF VRAM requirements. Everything that runs here: what can the Mac mini M4 Pro 48 GB run?

Other models that run on Mac mini M4 Pro 48 GB

Questions

Can CodeLlama 7B HF run on Mac mini M4 Pro 48 GB?

CodeLlama 7B HF at 8-bit runs on the M4 Pro 48 GB with 16K of context at about 29 tokens a second.

Report VR-0Q5IN70, calculated Nov 22, 2026 from published specs, not benchmarked.