qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark
qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark is vLLM TP=2 cookbook for RadixArk/Qwen3.8-Flash-Next-NVFP4 on 2x DGX Spark (GB10). - sfxnz/Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark. It is ranked #998 on the Dev Radar, in Hosting & infra, first seen 15 days ago and shared in 2 posts (3.8k views).
GitHub - sfxnz/Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark: vLLM TP=2 cookbook for RadixArk/Qwen3.8-Flash-Next-NVFP4 on 2x DGX Spark (GB10). · 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 }} sfxnz / Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark Public Notifications You must be signed in to change notification settings Fork 0 Star 0…
What people said about qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark on X
Qwen3.8-Flash-Next on 2x DGX sparks now serves NVIDIA's official ModelOpt NVFP4 🔥 262k native context c=1 37.5 tok/s → 44 tok/s c=2 34.9 tok/s → 36.2 tok/s https://github.com/sfxnz/Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark
— @sfxnz, 14 days ago · 21 likes · see the post
If you've been like me and still haven't tried Qwen3.8-Flash-Next NVFP4 because you've been so busy with GLM and Deepseek... I've battle tested and put this recipe through the trenches. c=1 40tok/s prose try it on 2 sparks and let me know how it goes. https://github.com/sfxnz/Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark
— @sfxnz, 15 days ago · 11 likes · see the post
Alternatives to qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark
- boat by ASCII — ascii box is now boat ( )
- Railway — Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin…
- Nebius Token Factory — Start building
- recipes.vllm.ai — DeepSeek's first experimental multimodal V4 model — the V4-Flash MoE backbone plus a 32-layer vision tower, 1M…
- click.alibabacloud.com — Model Studio
- serverkit — ServerKit is a lightweight, modern server control panel for managing web applications, databases, and services on your…
qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark in numbers
- Rank on the Dev Radar: #998 of 1353
- Shared in 2 posts by 1 account: @sfxnz
- 3.8k views on those posts
- First seen 15 days ago, last shared 14 days ago
- Pricing seen by Jev: open source
- Market: Hosting & infra
FAQ
What is qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark?
vLLM TP=2 cookbook for RadixArk/Qwen3.8-Flash-Next-NVFP4 on 2x DGX Spark (GB10). - sfxnz/Qwen3.8-Flash-Next-NVFP4-vLLM-2x-DGX-Spark It was first shared on X 15 days ago and is ranked #998 on the Dev Radar.
Is qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark free?
It is open source.
Who shared qwen3.8-flash-next-nvfp4-vllm-2x-dgx-spark?
1 account on X, including @sfxnz, in 2 posts totalling 3.8k 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. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.