Skip to content

MiniMax M2.7 on M5 Ultra 512 GB: VRAM, speed and fit

MiniMax M2.7 at FP8 runs on the M5 Ultra 512 GB with 200K of context at about 46 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Ultra 512 GB · FP8 · Ollama / LM Studio · Chat

GPU memory
391 GB
of 512 GB
Context
200K
auto
Speed
46 tok/s
11 when full
First reply
1.8 s
2K prompt

Where the memory goes

Model
214 GB
Context
48.4 GB
Overhead
743 MB
OS
128 GB
Free
121 GB
Memory
391 GB of 512 GB
Context
200K tokens · auto
Speed
46 tok/s · 11 when full
First reply
1.8 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What MiniMax M2.7 on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable263 GB neededPass
Headroom5% free121 GB free (31%)Pass
Context for chat16K or more200KPass
Writing speed15 tok/s or more46 tok/sPass
First replyunder 3 s, 2K prompt1.8 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
MiniMax M2.7
Parameters
229B, 10B active
Precision
FP8
Context
200K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Ultra 512 GB
GPU can use
384 GB of 512 GB

Running cost

At home
$5.06/mo
231 W at the wall
Renting instead
$574/mo
8× A40 at $4.72/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/MiniMax-M2.7-GGUF
vLLM
vllm serve MiniMaxAI/MiniMax-M2.7
MLX (Mac)
mlx_lm.chat --model mlx-community/MiniMax-M2.7-4bit

MiniMax M2.7 on similar machines

All machines: MiniMax M2.7 VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?

Other models that run on M5 Ultra 512 GB

Questions

Can MiniMax M2.7 run on M5 Ultra 512 GB?

MiniMax M2.7 at FP8 runs on the M5 Ultra 512 GB with 200K of context at about 46 tokens a second.

Report VR-0N4YU1D, calculated Nov 22, 2026 from published specs, not benchmarked.