Skip to content

Qwen2.5 Coder 7B Instruct on Mac mini M4 24 GB: VRAM, speed and fit

Qwen2.5 Coder 7B Instruct at 8-bit runs on the M4 24 GB with 32K of context at about 13 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 24 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
17.9 GB
of 24.0 GB
Context
32K
auto
Speed
13 tok/s
10 when full
First reply
9.2 s
2K prompt

Where the memory goes

Model
7.5 GB
Context
1.8 GB
Overhead
665 MB
OS
8.0 GB
Free
6.1 GB
Memory
17.9 GB of 24.0 GB
Context
32K tokens · auto
Speed
13 tok/s · 10 when full
First reply
9.2 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What Qwen2.5 Coder 7B Instruct on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable9.9 GB neededPass
Headroom5% free6.1 GB free (38%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more13 tok/sCheck
First replyunder 3 s, 2K prompt9.2 sFails

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
Qwen2.5 Coder 7B Instruct
Parameters
7.6B
Precision
8-bit (Q8_0)
Context
32K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 24 GB
GPU can use
16.0 GB of 24.0 GB

Running cost

At home
$0.85/mo
39 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 21, 2026.

How to run it

llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-7B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-Coder-7B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen2.5.1-Coder-7B-Instruct-4bit

Qwen2.5 Coder 7B Instruct on similar machines

All machines: Qwen2.5 Coder 7B Instruct VRAM requirements. Everything that runs here: what can the Mac mini M4 24 GB run?

Other models that run on Mac mini M4 24 GB

Questions

Can Qwen2.5 Coder 7B Instruct run on Mac mini M4 24 GB?

Qwen2.5 Coder 7B Instruct at 8-bit runs on the M4 24 GB with 32K of context at about 13 tokens a second.

Report VR-1A6VNEO, calculated Nov 22, 2026 from published specs, not benchmarked.