Skip to content

MiniMax M2 on Dual DGX Spark: VRAM, speed and fit

MiniMax M2 at FP8 runs on the DGX Spark 128 GB with 52K of context at about 15 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · FP8 · Ollama / LM Studio · Chat

GPU memory
243 GB
of 256 GB
Context
52K
auto
Speed
15 tok/s
7.4 when full
First reply
2.8 s
2K prompt

Where the memory goes

Model
214 GB
Context
12.6 GB
Overhead
1.2 GB
OS
15.4 GB
Free
12.6 GB
Memory
243 GB of 256 GB
Context
52K tokens · auto
Speed
15 tok/s · 7.4 when full
First reply
2.8 s for a 2K prompt
Running cost
$3.15/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What MiniMax M2 on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable228 GB neededPass
Headroom5% free12.6 GB free (5%)Pass
Context for chat16K or more52KPass
Writing speed15 tok/s or more15 tok/sPass
First replyunder 3 s, 2K prompt2.8 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
Parameters
229B, 11.6B active
Precision
FP8
Context
52K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Spark 128 GB
GPU can use
241 GB of 256 GB

Worth trying

  • 8-bit cache: Room for 96K context

Running cost

At home
$3.15/mo
144 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-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 Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can MiniMax M2 run on Dual DGX Spark?

MiniMax M2 at FP8 runs on the DGX Spark 128 GB with 52K of context at about 15 tokens a second.

Report VR-11TKK0N, calculated Nov 22, 2026 from published specs, not benchmarked.