Who needs more than one Spark?
This is a dev post classified by AGK Intelligence as Hosting & infra (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Who needs more than one Spark? Definitely not everyone. Why? Take a loot at this: @MiaAI_lab's Qwen3.8-Flash-Next recipe on one DGX Spark reached her README numbers on code: 114.3 tok/s. 114 tok/s on one Spark! And we aren't talking about Qwen 3.6 35B here. This is a 180 billion parameter model! I ran her recipe as published, commit fd3f43e, TensorFold v1.1.4. Measured with sparkDash 2.75.0, the tool from her README, on the Spark itself. 2048 tokens per request, mean of 2 runs, Oct 29. My Spark runs with a 2200 MHz clock cap. Code, 1 request: Mine: 114.3 tok/s Her README: 110.5 tok/s Cod
Posted by Niklas (2.3k followers) 1 days ago · 46 likes · 4.7k views · view the original post on X. Kept by the Dev Radar as Hosting & infra. Tools mentioned: qwen3.8-flash-next-single-dgx-spark-tensorfold.
More dev work like this
- I like that our @googlecloud spend caps (for Gemini API, Cloud Run, Gemini platform) now… — @rseroter
- Sleeper GPU of the Week 💤 — @vast_ai
- The era of personal software is so wild — @allietheicon
- Your first Kubernetes cluster and your tenth should install and upgrade the same way. — @CtrlIQ
- #developers, Love using #Slack to deploy and manage your apps? Now chat with #Slackbot… — @scottcjohnston
- Using Akash Console with other people used to mean sharing one login. No more. — @akashnet
- Regenerating database passwords or bucket credentials in the dashboard now automatically… — @Railway
- Este repo tiene miles de ejercicios para DevOps, arquitectura y servidores. — @midudev
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.