Skip to content

Gemma 4 26B A4B on M5 Max 128 GB: VRAM, speed and fit

Gemma 4 26B A4B at 8-bit runs on the M5 Max 128 GB with 256K of context at about 77 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
61.1 GB
of 128 GB
Context
256K
auto
Speed
77 tok/s
52 when full
First reply
1.1 s
2K prompt

Where the memory goes

Model
25.5 GB
Context
2.7 GB
Overhead
856 MB
OS
32.0 GB
Free
66.9 GB
Memory
61.1 GB of 128 GB
Context
256K tokens · auto
Speed
77 tok/s · 52 when full
First reply
1.1 s for a 2K prompt
Running cost
$2.63/mo at home · $58/mo on a cloud 2× RTX 2000 Ada

Validation: Validated

What Gemma 4 26B A4B on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable29.1 GB neededPass
Headroom5% free66.9 GB free (70%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more77 tok/sPass
First replyunder 3 s, 2K prompt1.1 sPass

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
8-bit (Q8_0)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Max 128 GB
GPU can use
96.0 GB of 128 GB

Running cost

At home
$2.63/mo
120 W at the wall
Renting instead
$58/mo
2× RTX 2000 Ada at $0.48/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

All machines: Gemma 4 26B A4B VRAM requirements. Everything that runs here: what can the M5 Max 128 GB run?

Other models that run on M5 Max 128 GB

Questions

Can Gemma 4 26B A4B run on M5 Max 128 GB?

Gemma 4 26B A4B at 8-bit runs on the M5 Max 128 GB with 256K of context at about 77 tokens a second.

Report VR-025FWOY, calculated Nov 22, 2026 from published specs, not benchmarked.