qwen3.8-flash-next-1x-dgx-spark
qwen3.8-flash-next-1x-dgx-spark is Qwen3.8-Flash-Next (125B MoE, 6B active) on a single NVIDIA DGX Spark: llama.cpp qwen4exp/mtp + Unsloth UD-Q4_K_XL, measured MTP draft sweep, 47 tok/s code - Weschera/Qwen3.8-Flash-Next-1x-DGX-Spark. It is ranked #1271 on the Dev Radar, in Other, first seen 17 days ago and shared in 1 post (13.1k views).
GitHub - Weschera/Qwen3.8-Flash-Next-1x-DGX-Spark: Qwen3.8-Flash-Next (125B MoE, 6B active) on a single NVIDIA DGX Spark: llama.cpp qwen4exp/mtp + Unsloth UD-Q4_K_XL, measured MTP draft sweep, 47 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 / Qwen3.8-Flash-Next-1x-DGX-Spark Public Notifications You must…
What people said about qwen3.8-flash-next-1x-dgx-spark on X
Qwen3.8-Flash-Next (125B MoE, 6B active) One DGX Spark recipe: llama.cpp qwen4exp/mtp branch + @UnslothAI UD-Q4_K_XL (103.7 GB fits the 121 GB GB10) Measured MTP draft sweep: code 47 tok/s (90% accept), thinking 37-39, prose 24. n=4 beats the default n=5. Full recipe + raw evidence:…
— @WescheNex1q, 17 days ago · 85 likes · see the post
Alternatives to qwen3.8-flash-next-1x-dgx-spark
- Ling-3.0-flash-Fin — Qwen-Drive-1.0-4B is a vision-language foundation model that handles 3D perception, driving VQA, and motion planning…
- Cactus Compute — It runs on mobiles, wearables, smart home devices, small robots and microcontrollers, with prebuilt engines for macOS,…
- bespoke-nimble-9b — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- orcabonsai-27b-uncensored — Open source
- 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…
- deepseek-v4.1-flash — Original safetensors
qwen3.8-flash-next-1x-dgx-spark in numbers
- Rank on the Dev Radar: #1271 of 1578
- Shared in 1 post by 1 account: @WescheNex1q
- 13.1k views on those posts
- First seen 17 days ago, last shared 17 days ago
- Pricing seen by Jev: open source
- Market: Other
FAQ
What is qwen3.8-flash-next-1x-dgx-spark?
Qwen3.8-Flash-Next (125B MoE, 6B active) on a single NVIDIA DGX Spark: llama.cpp qwen4exp/mtp + Unsloth UD-Q4_K_XL, measured MTP draft sweep, 47 tok/s code - Weschera/Qwen3.8-Flash-Next-1x-DGX-Spark It was first shared on X 17 days ago and is ranked #1271 on the Dev Radar.
Is qwen3.8-flash-next-1x-dgx-spark free?
It is open source.
Who shared qwen3.8-flash-next-1x-dgx-spark?
1 account on X, including @WescheNex1q, in 1 post totalling 13.1k 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. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.