Skip to content

Qwen3 8B on Mac mini M4 Pro 48 GB: VRAM, speed and fit

Qwen3 8B at 8-bit runs on the M4 Pro 48 GB with 40K of context at about 26 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
26.4 GB
of 48.0 GB
Context
40K
auto
Speed
26 tok/s
15 when full
First reply
5.0 s
2K prompt

Where the memory goes

Model
8.1 GB
Context
5.6 GB
Overhead
681 MB
OS
12.0 GB
Free
21.6 GB
Memory
26.4 GB of 48.0 GB
Context
40K tokens · auto
Speed
26 tok/s · 15 when full
First reply
5.0 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 Qwen3 8B on Mac mini M4 Pro 48 GB was checked against
CheckTargetResultStatus
Fits in GPU memory36.0 GB usable14.4 GB neededPass
Headroom5% free21.6 GB free (60%)Pass
Context for chat16K or more40KPass
Writing speed15 tok/s or more26 tok/sPass
First replyunder 3 s, 2K prompt5.0 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
Qwen3 8B
Parameters
8.2B
Precision
8-bit (Q8_0)
Context
40K, 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 21, 2026.

How to run it

llama.cpp
llama-server -hf Qwen/Qwen3-8B-GGUF
vLLM
vllm serve Qwen/Qwen3-8B
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-8B-4bit

Qwen3 8B on similar machines

All machines: Qwen3 8B 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 Qwen3 8B run on Mac mini M4 Pro 48 GB?

Qwen3 8B at 8-bit runs on the M4 Pro 48 GB with 40K of context at about 26 tokens a second.

Report VR-13TVM02, calculated Nov 22, 2026 from published specs, not benchmarked.