NVIDIA Developer Forums
NVIDIA Developer Forums is Dual Spark. It is ranked #98 on the Dev Radar, in Hosting & infra, first seen 2 days ago and shared in 4 posts (487.5k views).
Visit forums.developer.nvidia.com
What NVIDIA Developer Forums says about itself
V5 coming by tomorrow, +cca 20% vs v4: Coding: game-bench 1 2 4 8 (3000-token runs) C1: 29.81 tok/s C2: 42.00 agg / 21.00 mean stream C4: 58.00 agg / 14.50 mean stream C8: 87.12 agg / 10.89 mean stream Prose: llama-bench coherent corpus model test t/s peak t/s KIMI-K3 pp2048 @ d4000 880.35 ± 0.00 KI
Full Kimi K3 running on 16x GB10 cluster - #141 by ciprianveg - DGX Spark / GB10 Projects - NVIDIA Developer Forums = 40rem)" rel="stylesheet" data-target="discourse-ai_desktop" /> = 40rem)" rel="stylesheet" data-target="discourse-events_desktop" /> = 40rem)" rel="stylesheet" data-target="discourse-reactions_desktop" /> = 40rem)" rel="stylesheet" data-target="poll_desktop" /> = 40rem)" rel="stylesheet" data-target="desktop_theme" data-theme-id="13" data-theme-name="discourse-nvidia-theme"/>…
What people said about NVIDIA Developer Forums on X
Great speed-up: Full Kimi K3 — the 2.8T-parameter model running on 16× NVIDIA GB10 (Spark) - V5 coming by tomorrow, cca 20% faster and much improved concurrency: (~30t/s C1, 87t/s C8 ) 136t/s peak speed at C8: Coding: game-bench 1 2 4 8 (3000-token runs) C1: 29.81 tok/s C2: 42.00 agg / 21.00 mean stream C4: 58.00 agg…
— @ciprianveg, 2 days ago · 241 likes · see the post
**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
Full Kimi K3 (2.8T) frontier model running locally on 16× NVIDIA GB10 Spark Desk cluster, Not a data center. - 30 t/s single stream - 87 t/s aggregate at C8 - 136 t/s peak claimed - Prose llama-bench holding 20–23 t/s generate even at long context. You don’t need a hyperscaler rack to run a 2.8T model anymore.
— @0x0SojalSec, 2 days ago · 96 likes · see the post
Alternatives to NVIDIA Developer Forums
- 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…
NVIDIA Developer Forums in numbers
- Rank on the Dev Radar: #98 of 2352
- Shared in 4 posts by 3 accounts: @ciprianveg, @0x0SojalSec, @cozybearlog
- 487.5k views on those posts
- First seen 2 days ago, last shared 11 h ago
- Pricing seen by Jev: not stated
- Market: Hosting & infra
FAQ
What is NVIDIA Developer Forums?
Dual Spark It was first shared on X 2 days ago and is ranked #98 on the Dev Radar.
Is NVIDIA Developer Forums free?
Pricing is not stated on the page we read.
Who shared NVIDIA Developer Forums?
3 accounts on X, including @ciprianveg, @0x0SojalSec, @cozybearlog, in 4 posts totalling 487.5k 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 08:21 UTC. Full method.