Skip to content

Medgemma 1.5 4B IT on Mac mini M4 16 GB: VRAM, speed and fit

Medgemma 1.5 4B IT at 8-bit runs on the M4 16 GB with 128K of context at about 24 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
13.0 GB
of 16.0 GB
Context
128K
auto
Speed
24 tok/s
14 when full
First reply
4.3 s
2K prompt

Where the memory goes

Model
4.3 GB
Context
2.6 GB
Overhead
848 MB
OS
5.3 GB
Free
3.0 GB
Memory
13.0 GB of 16.0 GB
Context
128K tokens · auto
Speed
24 tok/s · 14 when full
First reply
4.3 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 Medgemma 1.5 4B IT on Mac mini M4 16 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.7 GB usable7.7 GB neededPass
Headroom5% free3.0 GB free (28%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more24 tok/sPass
First replyunder 3 s, 2K prompt4.3 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
Medgemma 1.5 4B IT
Parameters
4.3B
Precision
8-bit (Q8_0)
Context
128K, 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

llama.cpp
llama-server -hf unsloth/medgemma-1.5-4b-it-GGUF
vLLM
vllm serve google/medgemma-1.5-4b-it

Medgemma 1.5 4B IT on similar machines

All machines: Medgemma 1.5 4B IT 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 Medgemma 1.5 4B IT run on Mac mini M4 16 GB?

Medgemma 1.5 4B IT at 8-bit runs on the M4 16 GB with 128K of context at about 24 tokens a second.

Report VR-055YOYV, calculated Nov 22, 2026 from published specs, not benchmarked.