Skip to content

Ministral 3 8B on Mac mini M4 32 GB: VRAM, speed and fit

Ministral 3 8B at 8-bit runs on the M4 32 GB with 80K of context at about 11 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
30.7 GB
of 32.0 GB
Context
80K
auto
Speed
11 tok/s
4.8 when full
First reply
11 s
2K prompt

Where the memory goes

Model
8.8 GB
Context
10.6 GB
Overhead
640 MB
OS
10.7 GB
Free
1.3 GB
Memory
30.7 GB of 32.0 GB
Context
80K tokens · auto
Speed
11 tok/s · 4.8 when full
First reply
11 s for a 2K prompt
Running cost
$0.85/mo at home · $33/mo on a cloud RTX A5000

Validation: Not validated

What Ministral 3 8B on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable20.1 GB neededPass
Headroom5% free1.3 GB free (6%)Pass
Context for chat16K or more80KPass
Writing speed15 tok/s or more11 tok/sCheck
First replyunder 3 s, 2K prompt11 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
Ministral 3 8B
Parameters
8.9B
Precision
8-bit (Q8_0)
Context
80K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 32 GB
GPU can use
21.3 GB of 32.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/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

Ollama
ollama run ministral-3:8b
llama.cpp
llama-server -hf unsloth/Ministral-3-8B-Instruct-2512-GGUF
vLLM
vllm serve mistralai/Ministral-3-8B-Instruct-2512
MLX (Mac)
mlx_lm.chat --model mlx-community/Ministral-3-8B-Instruct-2512-4bit

Ministral 3 8B on similar machines

All machines: Ministral 3 8B VRAM requirements. Everything that runs here: what can the Mac mini M4 32 GB run?

Other models that run on Mac mini M4 32 GB

Questions

Can Ministral 3 8B run on Mac mini M4 32 GB?

Ministral 3 8B at 8-bit runs on the M4 32 GB with 80K of context at about 11 tokens a second.

Report VR-024SR2D, calculated Nov 22, 2026 from published specs, not benchmarked.