Skip to content

Pixtral 12B on Mac mini M4 Pro 48 GB: VRAM, speed and fit

Pixtral 12B at 8-bit runs on the M4 Pro 48 GB with 128K of context at about 17 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
45.2 GB
of 48.0 GB
Context
128K
auto
Speed
17 tok/s
6.4 when full
First reply
8.1 s
2K prompt

Where the memory goes

Model
12.5 GB
Context
20.0 GB
Overhead
672 MB
OS
12.0 GB
Free
2.8 GB
Memory
45.2 GB of 48.0 GB
Context
128K tokens · auto
Speed
17 tok/s · 6.4 when full
First reply
8.1 s for a 2K prompt
Running cost
$1.84/mo at home · $61/mo on a cloud 2× RTX A4500

Validation: Not validated

What Pixtral 12B on Mac mini M4 Pro 48 GB was checked against
CheckTargetResultStatus
Fits in GPU memory36.0 GB usable33.2 GB neededPass
Headroom5% free2.8 GB free (8%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more17 tok/sPass
First replyunder 3 s, 2K prompt8.1 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
Pixtral 12B
Parameters
12.7B
Precision
8-bit (Q8_0)
Context
128K, 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
$61/mo
2× RTX A4500 at $0.50/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 ggml-org/pixtral-12b-GGUF
vLLM
vllm serve mistral-experimental/pixtral-12b

Pixtral 12B on similar machines

All machines: Pixtral 12B 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 Pixtral 12B run on Mac mini M4 Pro 48 GB?

Pixtral 12B at 8-bit runs on the M4 Pro 48 GB with 128K of context at about 17 tokens a second.

Report VR-0DXXK3L, calculated Nov 22, 2026 from published specs, not benchmarked.