Skip to content

Qwen3.5 4B on Mac mini M4 16 GB: VRAM, speed and fit

Qwen3.5 4B at 8-bit runs on the M4 16 GB with 144K of context at about 19 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 16 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
15.3 GB
of 16.0 GB
Context
144K
auto
Speed
19 tok/s
9.8 when full
First reply
5.7 s
2K prompt

Where the memory goes

Model
4.6 GB
Context
4.5 GB
Overhead
821 MB
OS
5.3 GB
Free
723 MB
Memory
15.3 GB of 16.0 GB
Context
144K tokens · auto
Speed
19 tok/s · 9.8 when full
First reply
5.7 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Validated with conditions

What Qwen3.5 4B on Mac mini M4 16 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.7 GB usable10.0 GB neededPass
Headroom5% free723 MB free (7%)Pass
Context for chat16K or more144KPass
Writing speed15 tok/s or more19 tok/sPass
First replyunder 3 s, 2K prompt5.7 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
Qwen3.5 4B
Parameters
4.7B
Precision
8-bit (Q8_0)
Context
144K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 16 GB
GPU can use
10.7 GB of 16.0 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 22, 2026.

How to run it

Ollama
ollama run qwen3.5:4b
llama.cpp
llama-server -hf unsloth/Qwen3.5-4B-GGUF
vLLM
vllm serve Qwen/Qwen3.5-4B
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3.5-4B-MLX-4bit

Qwen3.5 4B on similar machines

All machines: Qwen3.5 4B VRAM requirements. Everything that runs here: what can the Mac mini M4 16 GB run?

Other models that run on Mac mini M4 16 GB

Questions

Can Qwen3.5 4B run on Mac mini M4 16 GB?

Qwen3.5 4B at 8-bit runs on the M4 16 GB with 144K of context at about 19 tokens a second.

Report VR-18CFG50, calculated Nov 22, 2026 from published specs, not benchmarked.