← What do you want to do?

Recipe by Mia's AI Lab · AGPL-3.0 · Built on Xiaomi, SGLang, NVIDIA

Two DGX Sparks · Build a web app

MiMo-V2.6-Flash

Its creator tested it on two DGX Sparks, and it is the strongest model with a working test there for this.

Tested by Mia's AI Lab on two DGX Sparks. See their results.

Advanced: link the Sparks with cables and set up NVIDIA Sync first. NVIDIA guide

  1. Open a coding agent on the Spark (Claude Code, Codex or Cursor).
  2. Paste this prompt:
Set up Mia’s AI Lab recipe for MiMo-V2.6-Flash on my two DGX Sparks: https://github.com/MiaAI-Lab/MiMo-V2.6-Flash-2x-DGX-Sparks
Follow its README exactly. Run everything on Spark 1 (the head).
1. Check first: the cable link is up, SSH from Spark 1 to Spark 2 works, Docker works, about 161 GiB free disk on Spark 1. Stop and tell me if not.
2. Clone the repo, run ./start.sh doctor, and set the IPs in .env.
3. Run ./start.sh download, build, share and serve, in that order.
4. Run ./start.sh smoke and tell me the result.
Ask me before changing network settings or deleting anything.

What happens next

Details

TWO DGX SPARKS · WEB APPS

MODELMiMo-V2.6-Flash MXFP4 experts, FP8 attention (as shipped)
RUN
git clone https://github.com/MiaAI-Lab/MiMo-V2.6-Flash-2x-DGX-Sparks.git
cd MiMo-V2.6-Flash-2x-DGX-Sparks
./start.sh doctor   # then set the IPs in .env
./start.sh download && ./start.sh build && ./start.sh share && ./start.sh serve
LEVELADVANCED Needs the QSFP cable link and the NVIDIA Sync cluster setup. NVIDIA
TESTED BYMia's AI Lab on 2 Sparks: 35 tok/s prose, 46 code, one request. Their results (benchmark table).
RECIPEMiMo-V2.6-Flash on two DGX Sparks. Full steps, fixes and credits.
SCOREArena WebDev 1634 ±9 (Oct 19)
AA CHECKDisagrees. Higher on AA: GLM-5.3-Flash (42).
RECIPEMiMo-V2.6-Flash on two DGX Sparks: every step, fixes and full credits.
COMMAND
git clone https://github.com/MiaAI-Lab/MiMo-V2.6-Flash-2x-DGX-Sparks.git
cd MiMo-V2.6-Flash-2x-DGX-Sparks
./start.sh doctor   # then set the IPs in .env
./start.sh download && ./start.sh build && ./start.sh share && ./start.sh serve
If it fails

  • A Spark runs out of memory during load.

    Use the SGLang image named in the README or newer. Older engines expand the experts and take the node down.

HOW WE PICK

  • A pick needs a recipe whose author published a working run on this many Sparks. That run is the fit proof, so we use no memory estimate here. Ranking is the same: Arena board per job, Artificial Analysis for long documents.
  • Only recipes with files at 4-bit or better.
  • Long documents: only runs that published a test with a prompt of 128K tokens or more.
  • Same model in two recipes: the faster tested run wins.
  • Our judgment: under 15 tok/s is too slow for everyday use. Where a published test shows a model below that, it cannot be the main pick; it moves to an ALSO line.
  • A main pick needs a published benchmark table, log or reproducible command output. A lone summary number is not enough; that recipe moves to an ALSO line.
  • Sometimes no model tested here has an Arena score for a job. Sometimes one without an Arena score beats the Arena pick on Artificial Analysis. Then we rank the whole job by the Artificial Analysis index instead, and say so on the SCORE line.

RunCards does not test recipes. TESTED BY is the recipe author's own published run. CLOSE means the two scores' margins overlap, so the order could flip. Scores checked 2026-10-19.