Local AI · Recipe · 8× RTX PRO 6000

Qwen3.8-Flash-Next FP8 with vLLM on 8× RTX PRO 6000

Qwen3.8-Flash-Next FP8 with vLLM on 8× RTX PRO 6000: 202 tok/s according to github.com (dataset as of Nov 3, 2026).

by helixml

202tok/sPeak

1 request, best value reported by source, with MTP3

Source: github.com

Intelligence (original model) · Artificial Analysis40with thinking

Instructions in the README Repo

Engine: vLLM (vllm/vllm-openai@sha256:0aea3024…, 2× TP4 + Expert-Parallel, MTP3) hinter ramjet v0.8.0
Quantization: FP8 (offizieller Checkpoint Qwen/Qwen3.8-Flash-Next-FP8)
Model family: Qwen3.8-Flash-Next
Context: 262,144
Creator: helixml
GitHub stars: 9
Repo updated: Oct 26, 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

Peak (decode)202 tok/sREADME „Models with a validated stack“: Decode @ c1 113 → 202 tok/s mit MTP3 (+79 %), 2× TP4+EP; Full-Box-Peak 3.340,5 tok/s (c64) Source

What you need

Hardware: 8 × NVIDIA RTX PRO 6000 Blackwell
Weights: Main weightsQwen/Qwen3.8-Flash-Next-FP8 other
BaseQwen/Qwen3.8-Flash-Next other
Engine: vLLM (vllm/vllm-openai@sha256:0aea3024…, 2× TP4 + Expert-Parallel, MTP3) hinter ramjet v0.8.0
Context: 262,144 tokens

Sources

Related recipes

1× Mac

Qwen3.8-Flash-Next 125B-A6B MLX 4/8-bit with mlx-serve on 1× Mac (M5 Ultra)

by drowzeys

155tok/sEveryday

1 request, llmprobe standard prompt, thinking on, with MTP + PLD (per recipe) Source

Intelligence40with thinking

Experimental
License unclear

MLX mixed 4/8-bit (ddalcu, 100 GiB), KV bf16mlx-serve 26.9.7-dev @933566c, MLX 0.32.3 (NAX an)Weights Repo Updated Sep 30, 2026

Details

4× RTX 3090

Qwen3.8-Flash-Next 125B with llama.cpp on 4× RTX 3090

by tonyd2wild

110tok/sEveryday

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

Intelligence40with thinking

License unclear

W4A16 (vLLM) bzw. GGUFvLLM (Lane 1) / llama.cpp (Lane 2)Weights Repo Updated Oct 1, 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

4× DGX Spark

Qwen3.8-Flash-Next NVFP4 with SparkRing on 4× DGX Spark

by fujitsupolycom

73tok/sEveryday

1 request, decode at 32K context (speed table, ring of four), thinking on, xhigh Source

Intelligence40with thinking

Custom kernel required

NVFP4 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 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

← 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

Sources

Related recipes

Qwen3.8-Flash-Next 125B-A6B MLX 4/8-bit with mlx-serve on 1× Mac (M5 Ultra)

Qwen3.8-Flash-Next 125B with llama.cpp on 4× RTX 3090

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 NVFP4 with SparkRing on 4× DGX Spark

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

Local AI in your company?