IT
Prenoti una chiamata

Local AI · Recipe · 1× DGX Spark

Qwen3.8-Flash-Next INT4-AutoRound (v5.2) on 1× DGX Spark

Qwen3.8-Flash-Next INT4-AutoRound (v5.2) on 1× DGX Spark: 86.3 tok/s according to github.com (dataset as of Sep 29, 2026).

by myllmbox

86.3tok/sPeak

1 request, code prompt (TypeScript), thinking off, v5.2 table

Source: github.com
Intelligence (original model) · Artificial Analysis40with thinking
Instructions in the README Repo

Engine

Engine
vLLM 0.30 (RecoverSSM, dynamischer Draft-Depth bis 7, sampled Drafts mit Block-Verifikation, 16 Seats) — Kit v5.2
Quantization
INT4-AutoRound (azampatti): int4-Experten, fp8-Seitenschichten, fp8-n-gram-Tabelle (49 GB, von Disk)
Model family
Qwen3.8-Flash-Next
Context
—
Parameters
48 Layer, 512 Experten (MoE); 124 GB Safetensors
Creator
myllmbox
GitHub stars
120
Repo updated
Oct 5, 2026

Measurements

Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.

Decode · 1 request

  • Everyday (decode)64.7 tok/sMixed (code + explanation), c=1, Thinking off, Mittel aus 3 Runs Source 
  • Peak (decode)86.3 tok/sCode (TypeScript), c=1, Thinking off; Thinking-on-Peak (pasture): 110.8; Peak @16 Streams (mixed, Thinking off): 414 aggregiert Source 

Prefill by context

Time to first token

Shorter is better.

  • Prompt not stated1 mscontext 1K · 1k-Prompt, 0.57 s Source 

What you need

Hardware
1 × NVIDIA DGX Spark (GB10)
Engine
vLLM 0.30 (RecoverSSM, dynamischer Draft-Depth bis 7, sampled Drafts mit Block-Verifikation, 16 Seats) — Kit v5.2

Notes

What matters before you rebuild it.

  • Custom kernel required

Sources

Related recipes

2× DGX Spark

Qwen3.8-Flash-Next 125B INT4-AutoRound with TensorFold on 2× DGX Spark (1M context)

by MiaAI-Lab

89.3tok/sEveryday

1 request, prose prompt, with MTP (per recipe) Source 

Intelligenceno independent value
  • Custom kernel required
  • License unclear

INT4-AutoRound (GPTQ int4, Top-5-Experten) + FP8 n-gram-Tabelle, FP8 KVTensorFold tensorfold-native (Zig, zig-flashnext db281878 + patches), Image ghcr.io/miaai-lab/qwen3.8-flash-dual-dgx-sparks-tensorfold:zig-db28187-f3e1300f4f62, TP=2 über CX7/RoCE, MTP + Copy-Drafts (QUANT=int4ar)Weights Repo Updated Oct 8, 2026

Details
2× DGX Spark

Qwen3.8-Flash-Next INT4-AutoRound (v5.2) with vLLM on 2× DGX Spark

by myllmbox

74tok/sEveryday

1 request, prose prompt (long story), thinking off, with MTP Source 

Intelligence40with thinking
  • Custom kernel required
  • License unclear

INT4-AutoRound (azampatti): int4-Experten, fp8-Seitenschichten; n-gram-Tabelle beim Laden fp8 → NVFP4, halb pro Box auf der GPU; KV-Pin 29G/Box (1.829.182 Tokens)vLLM 0.30 (Image myllmbox/qwen38-flash-next-cluster-vllm:v5.2; RecoverSSM, dynamischer Draft-Depth 3–7 in Full-CUDA-Graphs, sampled Drafts + Block-Verifikation, One-Shot-RoCE-All-Reduce, Dual-Rail, TP=2, 64 Seats) — Kit v5.2Weights Repo Updated Oct 6, 2026

Details
2× DGX Spark

Qwen3.8-Flash-Next 125B NVFP4 with TensorFold on 2× DGX Spark (1M context)

by MiaAI-Lab

67.4tok/sEveryday

1 request, prose prompt, with MTP (per recipe) Source 

Intelligence40with thinking
  • Custom kernel required
  • License unclear

NVFP4 (nvidia, Experten) + FP8 n-gram/MTP, FP8 KVTensorFold tensorfold-native (Zig, zig-flashnext db281878 + patches), Image ghcr.io/miaai-lab/qwen3.8-flash-dual-dgx-sparks-tensorfold:zig-db28187-f3e1300f4f62, TP=2 über CX7/RoCE, MTP + Copy-DraftsWeights Repo Updated Oct 8, 2026

Details

← Back to overview

Local AI in your company?

In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.

See the AI workshopBack to overview