← What do you want to do?

Recipe by Mia's AI Lab · Apache-2.0 · Built on TensorFold, Z.ai, turboderp, IncoAI, Jay Leaton, NVIDIA

Two DGX Sparks · Code

GLM-5.3-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 GLM-5.3-Flash on my DGX Sparks: https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold
Follow its README exactly. Run everything on Spark 1 (the head).
1. Check first: the QSFP link is up and pings, SSH from Spark 1 to the worker works, Docker works, about 110 GiB free memory on each. Stop and tell me if not.
2. Clone the repo, copy scripts/local.sh.example to scripts/local.sh and set WORKER (and FABRIC_PEER if the README says so).
3. Run ./start.sh (or ./start-tp3.sh with WORKER2 for three Sparks).
4. Wait for “is now LIVE! on port 8888”, test /v1/models and tell me.
Ask me before changing network settings or deleting anything.

What happens next

Details

TWO DGX SPARKS · CODING

MODELGLM-5.3-Flash EXL3 4-bit experts and dense weights, FP8 cache
RUN
git clone https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold.git
cd GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold
cp scripts/local.sh.example scripts/local.sh   # set WORKER
./start.sh
LEVELADVANCED Needs the QSFP cable link and the NVIDIA Sync cluster setup. NVIDIA
TESTED BYMia's AI Lab on 2 Sparks: 60.4 tok/s, one request. Their results (benchmark table).
RECIPEGLM-5.3-Flash on two or three DGX Sparks (TensorFold). Full steps, fixes and credits.
SCOREArena Coding 1525 ±7 (Oct 15)
CLOSEMiMo-V2.6-Flash 1513 ±12 (recipe). Within the margin.
ALSO TESTEDTom Sarihan on 2 Sparks: 21.45 tok/s, one user. Their results (log or results file). Recipe.
AA CHECKAgrees.
RECIPEGLM-5.3-Flash on two or three DGX Sparks (TensorFold): every step, fixes and full credits.
COMMAND
git clone https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold.git
cd GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold
cp scripts/local.sh.example scripts/local.sh   # set WORKER
./start.sh
If it fails

  • “only N GiB memory available”.

    Other GPU work runs on that Spark. Stop it (docker ps) and restart.

  • “no RoCE device” or “no route”.

    The route to the worker skips the cable. Set FABRIC_PEER to the worker’s cable address.

  • Answers cut off.

    It thinks first. Give replies more max_tokens.

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.