Can NVIDIA DGX Spark (GB10) · 128 GB run MiMo-V2.6-Pro-RL (1T-A42B)?
128 GB unified · 273 GB/s memory bandwidth · MiMo-V2.6-Pro-RL (1T-A42B) has 1020B parameters (42B active per token).
Short answer
No. It doesn't fit in memory.
Needs ≈965 GB but only ≈120 GB is available after the OS, other apps and Open WebUI.
Why it doesn’t fit
Even its smallest practical version (fp8) needs about 965 GB for the model, its context memory and the runtime. After the operating system (≈4.0 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), NVIDIA DGX Spark (GB10) · 128 GB has about 120 GB left, so it’s 845 GB short.
Ways to make it work
Close everything else
Not enough on its own: with every other app closed it’s still about 842 GB short.
Pick a smaller model from the same family
No smaller MiMo model in our catalog runs well here. See the other models below.
Get more memory
You’d want at least 973 GB of memory in total. The machines below are the cheapest that run it comfortably.
Check your exact setup
These pages assume typical settings. A shorter context or a lighter chat app can change the answer.
Check NVIDIA DGX Spark (GB10) · 128 GB
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for NVIDIA DGX Spark (GB10) · 128 GB
The best-rated models for chat on this machine.
- gpt-oss-120b≈55 tok/sExcellent
- Recursive Flint (40B-A2.5B)100–140 tok/sExcellent
- Qwen3.6 35B-A3B60–80 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct60–80 tok/sExcellent
- Gemma 4 26B-A4B45–60 tok/sExcellent
- Qwen3.5 35B-A3B60–80 tok/sExcellent
Cheapest machines for MiMo-V2.6-Pro-RL (1T-A42B)
Hardware rated comfortable or better for chat, lowest price first.
No machine in our catalog runs it comfortably for chat.
Same chip, other memory: 64 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.