Skip to content

MiMo V2.6 Flash on Dual DGX Spark: VRAM, speed and fit

MiMo V2.6 Flash at FP4 + FP8 runs on the DGX Spark 128 GB with 1M of context at about 17 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · FP4 + FP8 · Ollama / LM Studio · Chat

GPU memory
200 GB
of 256 GB
Context
1M
auto
Speed
17 tok/s
5.4 when full
First reply
2.1 s
2K prompt

Where the memory goes

Model
161 GB
Context
22.5 GB
Overhead
1.1 GB
OS
15.4 GB
Free
55.9 GB
Memory
200 GB of 256 GB
Context
1M tokens · auto
Speed
17 tok/s · 5.4 when full
First reply
2.1 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Validated

What MiMo V2.6 Flash on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable185 GB neededPass
Headroom5% free55.9 GB free (23%)Pass
Context for chat16K or more1MPass
Writing speed15 tok/s or more17 tok/sPass
First replyunder 3 s, 2K prompt2.1 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
MiMo V2.6 Flash
Parameters
309B, 15B active
Precision
FP4 + FP8
Context
1M, 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

Running cost

At home
$3.15/mo
144 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/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 ggml-org/MiMo-V2.6-Flash-RL-GGUF
vLLM
vllm serve XiaomiMiMo/MiMo-V2.6-Flash-RL
MLX (Mac)
mlx_lm.chat --model mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8

MiMo V2.6 Flash on similar machines

All machines: MiMo V2.6 Flash VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can MiMo V2.6 Flash run on Dual DGX Spark?

MiMo V2.6 Flash at FP4 + FP8 runs on the DGX Spark 128 GB with 1M of context at about 17 tokens a second.

Report VR-0X8A052, calculated Nov 22, 2026 from published specs, not benchmarked.