Local AI · Recipe · 2× DGX Spark

DeepSeek-V4-Flash-Vision-Exp FP8 with vLLM on 2× DGX Spark

DeepSeek-V4-Flash-Vision-Exp FP8 with vLLM on 2× DGX Spark: 32.5 tok/s according to github.com (dataset as of Nov 3, 2026).

by r0b0tlab

32.5tok/sEveryday

1 request, prose prompt, with DSpark (adaptive verification) (per recipe)

Source: github.com

Intelligence (original model) · Artificial Analysisno independent value

Instructions in the README Repo

Engine: vLLM
Quantization: offizielle Gewichte + FP8 KV
Model family: DeepSeek-V4-Flash-Vision-Exp
Context: 1,048,576
Creator: r0b0tlab
GitHub stars: 5
Repo updated: Sep 3, 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)32.5 tok/scontext ~600 tok (PROSE med) · PROSE c1 med (~600 tok), 1M-Profil; unklar ob 600 = Prompt- oder Output-Länge Source
Mixed (decode)30 tok/scontext 512 in / 256 out random · C-ladder c1, 1M-Profil; TPOT 25.0 ms Source
Peak (decode)53.7 tok/sTD2W300 spelled 1–300 (Zähl-Workload), 1M-Profil; accept length 2.74; accept length 2.74 = mittlere akzeptierte Länge (kein Anteil) Source

What you need

Hardware: 2 × NVIDIA DGX Spark (GB10)
Weights: Main weightsdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp MIT
Engine: vLLM
Context: 1,048,576 tokens

Notes

What matters before you rebuild it.

Experimental
Custom kernel required

Sources

Related recipes

2× DGX Spark

DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark

by sfxnz

26.2tok/sEveryday

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

Intelligenceno independent value

Experimental
Custom kernel required

MXFP4-Experten, FP8-Attention, fp8-KV 12-GiB-Pin, DSpark-6vLLMWeights Repo Updated Sep 4, 2026

Details

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 26, 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 29, 2026

Details

2× DGX Spark

Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark

by sfxnz

69.6tok/sEveryday

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

Intelligence40with thinking

License unclear

MLX affine 4-bit (group 32) auf allen Linears inkl. n-gram-Tabellen und MTP-Head, KV bf16TensorFold v0.6.2 (56e2e3e), TP=2, Image tf-qwen38-flashnext:0.6.2 (nvcr.io/nvidia/pytorch:26.07-py3)Weights Repo Updated Oct 2, 2026

Details

2× DGX Spark

Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× DGX Spark

by fujitsupolycom

68tok/sEveryday

1 request, generation at 32K context (speed table, pair), thinking on, xhigh, with MTP3 (per recipe) Source

Intelligence40with thinking

Custom kernel required
License unclear

NVFP4/MXFP8 CSF QAD (Local Inference Lab)vLLM (local-inference-lab Fork) via SparkRing (SIRCL-Collectives, switchless RDMA ueber ConnectX-7), Image Release 2026.10.2Weights Repo Updated Nov 2, 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 26, 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 workshop Back to overview

Engine

Measurements

Decode · 1 request

What you need

Notes

Sources

Related recipes

DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark

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

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

Qwen3.8-Flash-Next MLX 4-bit with TensorFold on 2× DGX Spark

Qwen3.8-Flash-Next NVFP4/MXFP8 CSF with SparkRing on 2× DGX Spark

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

Local AI in your company?