qwen-flash-next-uncensored-fp8-2x-dgx-spark
qwen-flash-next-uncensored-fp8-2x-dgx-spark is Qwen3.8-Flash-Next Uncensored FP8 on 2x DGX Spark: vLLM TP2, MTP k=3, genuine 128K qualification. Measured: 51 tok/s code. - Weschera/qwen-flash-next-uncensored-fp8-2x-dgx-spark. It is ranked #1014 on the AI Radar, in AI infra & evals, first seen 11 days ago and shared in 1 post (2.8k views).
GitHub - Weschera/qwen-flash-next-uncensored-fp8-2x-dgx-spark: Qwen3.8-Flash-Next Uncensored FP8 on 2x DGX Spark: vLLM TP2, MTP k=3, genuine 128K qualification. Measured: 51 tok/s code. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Weschera / qwen-flash-next-uncensored-fp8-2x-dgx-spark Public Notifications You must be…
What people said about qwen-flash-next-uncensored-fp8-2x-dgx-spark on X
Recipe: uncensored Qwen3.8 Flash-Next FP8 on 2× DGX Spark (TP2, vLLM). From @OrcaRouter • 37.9 prose / 51.3 code tok/s (native MTP k=3, 84% acceptance) • True 128K: needles found at 16K/60K/110K prompts • Benchmarked 90.4/100 • Parity with SGLang's official cookbook numbers for this model Hard-won lesson included:…
— @WescheNex1q, 11 days ago · 24 likes · see the post
Alternatives to qwen-flash-next-uncensored-fp8-2x-dgx-spark
- Ling-3.0-flash-Fin — 🚀 ZDTaichu5.0-9B is now on ModelScope! 🤖
- classifier.dev — now outperforms jev and is free
- Jev API, Pricing & Playground — Jev is now available on the @vercel AI Gateway
- Darkbloom — Private AI inference through hardware-attested Apple Silicon providers. Your prompts stay encrypted, your data stays…
- glm-5.3-flash-exl3-2x-dgx-sparks — GLM-5.3 Flash EXL3 for 2-4x DGX Sparks. Contribute to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks development by…
- Intelligence Benchmarking — Detailed intelligence benchmarking methodology for LLM quality evaluations.
qwen-flash-next-uncensored-fp8-2x-dgx-spark in numbers
- Rank on the AI Radar: #1014 of 1190
- Shared in 1 post by 1 account: @WescheNex1q
- 2.8k views on those posts
- First seen 11 days ago, last shared 11 days ago
- Pricing seen by Jev: open source
- Market: AI infra & evals
FAQ
What is qwen-flash-next-uncensored-fp8-2x-dgx-spark?
Qwen3.8-Flash-Next Uncensored FP8 on 2x DGX Spark: vLLM TP2, MTP k=3, genuine 128K qualification. Measured: 51 tok/s code. - Weschera/qwen-flash-next-uncensored-fp8-2x-dgx-spark It was first shared on X 11 days ago and is ranked #1014 on the AI Radar.
Is qwen-flash-next-uncensored-fp8-2x-dgx-spark free?
It is open source.
Who shared qwen-flash-next-uncensored-fp8-2x-dgx-spark?
1 account on X, including @WescheNex1q, in 1 post totalling 2.8k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.