Skip to content

MiniMax M3 on M5 Max 128 GB: VRAM, speed and fit

MiniMax M3 at 1.6-bit runs on the M5 Max 128 GB with 64K of context at about 53 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat

GPU memory
122 GB
of 128 GB
Context
64K
auto
Speed
53 tok/s
28 when full
First reply
7.0 s
2K prompt

Where the memory goes

Model
82.0 GB
Context
7.5 GB
Overhead
839 MB
OS
32.0 GB
Free
5.7 GB
Memory
122 GB of 128 GB
Context
64K tokens · auto
Speed
53 tok/s · 28 when full
First reply
7.0 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Not validated

What MiniMax M3 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 more64KPass
Writing speed15 tok/s or more53 tok/sPass
First replyunder 3 s, 2K prompt7.0 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
MiniMax M3
Parameters
427B, 23B active
Precision
1.6-bit (IQ1_S)
Context
64K, 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
$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-M3-GGUF
vLLM
vllm serve MiniMaxAI/MiniMax-M3
MLX (Mac)
mlx_lm.chat --model mlx-community/MiniMax-M3-4bit

MiniMax M3 on similar machines

All machines: MiniMax M3 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 M3 run on M5 Max 128 GB?

MiniMax M3 at 1.6-bit runs on the M5 Max 128 GB with 64K of context at about 53 tokens a second.

Report VR-12J6E40, calculated Nov 22, 2026 from published specs, not benchmarked.