← What do you want to do?

Recipe by Mia's AI Lab · MIT · Built on TensorFold, Jürgen Schmied, NVIDIA, Qwen

DGX Spark · Read long documents

Qwen3.8-Flash-Next

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

Tested by Mia's AI Lab on one DGX Spark. See their results.

  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 Qwen3.8 Flash Next on one DGX Spark: https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold
Follow its README exactly.
1. Check first: Docker works, about 160 GB free disk, about 108 GiB of memory available. Stop and tell me if not.
2. Clone the repo and run ./start.sh. The first run builds the engine and downloads the model.
3. Wait for “is now LIVE! on port 8888”, then test /v1/models and tell me.
Ask me before deleting anything or stopping other programs.

What happens next

Details

ONE DGX SPARK · LONG DOCS

MODELQwen3.8-Flash-Next NVFP4 experts, MXFP8 attention (NVIDIA QAD)
RUN
git clone https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold.git
cd Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold
./start.sh
TESTED BYMia's AI Lab on one Spark: 46 to 55 tok/s, one request. Their results (benchmark table).
LONGTested with a 131,110-token prompt.
RECIPEQwen3.8 Flash Next on one DGX Spark (TensorFold). Full steps, fixes and credits.
SCOREArtificial Analysis 40 (Oct 19)
RECIPEQwen3.8 Flash Next on one DGX Spark (TensorFold): every step, fixes and full credits.
COMMAND
git clone https://github.com/MiaAI-Lab/Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold.git
cd Qwen3.8-Flash-Next-Single-DGX-Spark-TensorFold
./start.sh
If it fails

  • It refuses to start: not enough memory.

    Stop other GPU work on the Spark. The default needs about 108 GiB available at start.

  • TTFT looks slow from another computer.

    The link adds its round trip. Measure on the Spark itself.

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.