Skip to content

Mistral Small 3.2 24B on Mac mini M4 24 GB: VRAM, speed and fit

Mistral Small 3.2 24B at 3-bit runs on the M4 24 GB with 20K of context at about 8.4 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 24 GB · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
22.7 GB
of 24.0 GB
Context
20K
auto
Speed
8.4 tok/s
6.5 when full
First reply
32 s
2K prompt

Where the memory goes

Model
10.9 GB
Context
3.1 GB
Overhead
672 MB
OS
8.0 GB
Free
1.3 GB
Memory
22.7 GB of 24.0 GB
Context
20K tokens · auto
Speed
8.4 tok/s · 6.5 when full
First reply
32 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What Mistral Small 3.2 24B on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable14.7 GB neededPass
Headroom5% free1.3 GB free (8%)Pass
Context for chat16K or more20KPass
Writing speed15 tok/s or more8.4 tok/sCheck
First replyunder 3 s, 2K prompt32 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
Mistral Small 3.2 24B
Parameters
24B
Precision
3-bit (Q3_K_M)
Context
20K, 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

Worth trying

  • 8-bit cache: Room for 40K context

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 22, 2026.

How to run it

Ollama
ollama run mistral-small3.2:24b
llama.cpp
llama-server -hf unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF
vLLM
vllm serve mistralai/Mistral-Small-3.2-24B-Instruct-2506
MLX (Mac)
mlx_lm.chat --model mlx-community/Mistral-Small-3.2-24B-Instruct-2506-4bit

Mistral Small 3.2 24B on similar machines

Other models that run on Mac mini M4 24 GB

Questions

Can Mistral Small 3.2 24B run on Mac mini M4 24 GB?

Mistral Small 3.2 24B at 3-bit runs on the M4 24 GB with 20K of context at about 8.4 tokens a second.

Report VR-0RM7BR1, calculated Nov 22, 2026 from published specs, not benchmarked.