gb10-vllm
gb10-vllm is vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2 - ciprianveg/gb10-vllm. It is ranked #513 on the Dev Radar, in Hosting & infra, first seen 1 days ago and shared in 1 post (432.2k views).
GitHub - ciprianveg/gb10-vllm: vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2 · 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 }} ciprianveg / gb10-vllm Public Notifications You must be signed in to change notification settings Fork 9 Star 34 main Branches Tags Go to file Code…
What people said about gb10-vllm on X
**This is the 2.8T-parameter Kimi K3 running at ~30 tok/s on 16× NVIDIA DGX Spark.** Not a synthetic “it boots” test. 👇 **Actually generating. Usable speed.** A few weeks ago, the question was: *Can a model this big even run properly on a cluster of Sparks?* Then: *Can we make it fast enough to actually use? What…
— @ciprianveg, 1 days ago · 172 likes · see the post
Alternatives to gb10-vllm
- boat by ASCII — ascii box is now boat ( )
- mimo-v2.6-flash-2x-dgx-spark — It's Ready For 2 x DGX Sparks
- Railway — Bring context from your work and personal accounts into the same conversation. Connect your accounts in the plugin…
- qwen3.8-flash-next-exl3-dgx-spark-recipe — Serve Qwen3.8-Flash-Next (turboderp ExLlamaV3 pack) on one NVIDIA DGX Spark with vLLM + vllm-exl3 -…
- GitLab — GitLab brings the context, guardrails, and visibility agents need to ship safely at their own speed. See how
- ax — 🥳 Excited to start revealing what we've been working on in the last few months. First, we decided to reinvent…
gb10-vllm in numbers
- Rank on the Dev Radar: #513 of 2357
- Shared in 1 post by 1 account: @ciprianveg
- 432.2k views on those posts
- First seen 1 days ago, last shared 1 days ago
- Pricing seen by Jev: open source
- Market: Hosting & infra
FAQ
What is gb10-vllm?
vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2 - ciprianveg/gb10-vllm It was first shared on X 1 days ago and is ranked #513 on the Dev Radar.
Is gb10-vllm free?
It is open source.
Who shared gb10-vllm?
1 account on X, including @ciprianveg, in 1 post totalling 432.2k 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. 20.7k posts from 4.9k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 09:16 UTC. Full method.