Skip to content

MiniMax M3 on 4× RTX PRO 6000 Blackwell: VRAM, speed and fit

MiniMax M3 at 6-bit runs on the 4× RTX PRO 6000 Blackwell with 288K of context at about 54 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX PRO 6000 Blackwell · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
363 GB
of 384 GB
Context
288K
auto
Speed
54 tok/s
21 when full
First reply
0.4 s
2K prompt

Where the memory goes

Model
326 GB
Context
33.8 GB
Overhead
3.2 GB
OS
0.0 GB
Free
20.9 GB
Memory
363 GB of 384 GB
Context
288K tokens · auto
Speed
54 tok/s · 21 when full
First reply
0.4 s for a 2K prompt
Running cost
$33/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What MiniMax M3 on 4× RTX PRO 6000 Blackwell was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable363 GB neededPass
Headroom5% free20.9 GB free (5%)Pass
Context for chat16K or more288KPass
Writing speed15 tok/s or more54 tok/sPass
First replyunder 3 s, 2K prompt0.4 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 M3
Parameters
427B, 23B active
Precision
6-bit (Q6_K)
Context
288K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX PRO 6000 Blackwell
GPU can use
384 GB of 384 GB

Running cost

At home
$33/mo
1520 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 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

Other models that run on 4× RTX PRO 6000 Blackwell

Questions

Can MiniMax M3 run on 4× RTX PRO 6000 Blackwell?

MiniMax M3 at 6-bit runs on the 4× RTX PRO 6000 Blackwell with 288K of context at about 54 tokens a second.

Report VR-1YZCY38, calculated Nov 22, 2026 from published specs, not benchmarked.