Skip to content

Gemma 4 26B A4B on Mac mini M4 32 GB: VRAM, speed and fit

Gemma 4 26B A4B at 5-bit runs on the M4 32 GB with 216K of context at about 32 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 5-bit (Q5_K_M) · Ollama / LM Studio · Chat

GPU memory
30.9 GB
of 32.0 GB
Context
216K
auto
Speed
32 tok/s
18 when full
First reply
15 s
2K prompt

Where the memory goes

Model
17.1 GB
Context
2.3 GB
Overhead
856 MB
OS
10.7 GB
Free
1.1 GB
Memory
30.9 GB of 32.0 GB
Context
216K tokens · auto
Speed
32 tok/s · 18 when full
First reply
15 s for a 2K prompt
Running cost
$0.85/mo at home · $33/mo on a cloud RTX A5000

Validation: Not validated

What Gemma 4 26B A4B on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable20.2 GB neededPass
Headroom5% free1.1 GB free (5%)Pass
Context for chat16K or more216KPass
Writing speed15 tok/s or more32 tok/sPass
First replyunder 3 s, 2K prompt15 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
Gemma 4 26B A4B
Parameters
25.8B, 3.8B active
Precision
5-bit (Q5_K_M)
Context
216K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 32 GB
GPU can use
21.3 GB of 32.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/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 gemma4:26b
llama.cpp
llama-server -hf unsloth/gemma-4-26B-A4B-it-GGUF
vLLM
vllm serve google/gemma-4-26B-A4B-it
MLX (Mac)
mlx_lm.chat --model mlx-community/gemma-4-26b-a4b-it-4bit

Gemma 4 26B A4B on similar machines

Other models that run on Mac mini M4 32 GB

Questions

Can Gemma 4 26B A4B run on Mac mini M4 32 GB?

Gemma 4 26B A4B at 5-bit runs on the M4 32 GB with 216K of context at about 32 tokens a second.

Report VR-1W6OSND, calculated Nov 22, 2026 from published specs, not benchmarked.