Skip to content

MiniMax M2 on M5 Max 128 GB: VRAM, speed and fit

MiniMax M2 at 2-bit runs on the M5 Max 128 GB with 40K of context at about 55 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
122 GB
of 128 GB
Context
40K
auto
Speed
55 tok/s
25 when full
First reply
3.5 s
2K prompt

Where the memory goes

Model
79.9 GB
Context
9.7 GB
Overhead
743 MB
OS
32.0 GB
Free
5.7 GB
Memory
122 GB of 128 GB
Context
40K tokens · auto
Speed
55 tok/s · 25 when full
First reply
3.5 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated with conditions

What MiniMax M2 on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable90.3 GB neededPass
Headroom5% free5.7 GB free (6%)Pass
Context for chat16K or more40KPass
Writing speed15 tok/s or more55 tok/sPass
First replyunder 3 s, 2K prompt3.5 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
MiniMax M2
Parameters
229B, 11.6B active
Precision
2-bit (Q2_K)
Context
40K, 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

Worth trying

  • 8-bit cache: Room for 80K context

Running cost

At home
$2.63/mo
120 W at the wall
Renting instead
$131/mo
4× RTX A5000 at $1.08/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/MiniMax-M2-GGUF
vLLM
vllm serve MiniMaxAI/MiniMax-M2
MLX (Mac)
mlx_lm.chat --model mlx-community/MiniMax-M2-4bit

MiniMax M2 on similar machines

All machines: MiniMax M2 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 MiniMax M2 run on M5 Max 128 GB?

MiniMax M2 at 2-bit runs on the M5 Max 128 GB with 40K of context at about 55 tokens a second.

Report VR-0YMBENW, calculated Nov 22, 2026 from published specs, not benchmarked.