Dev Radar
Support
LiveUpdated 2026-11-05 00:17 UTC

GLM-5.3-Flash on my 2 DGX Sparks matches Mia's 47.8 tok/s with her test method, on her…

GLM-5.3-Flash on my 2 DGX Sparks matches Mia's 47.8 tok/s with her test method, on her recipe released today 2 DGX…

This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

GLM-5.3-Flash on my 2 DGX Sparks matches Mia's 47.8 tok/s with her test method, on her recipe released today 2 DGX Sparks, 256 GB Decode, code: 42.4 tok/s Decode, prose: 38.7 tok/s 500 words (code and prose): about 17.1 s First token at 8K: 4.9 s First token at 32K: 20.5 s First token at 128K: 77.0 s 8 requests at once: 80.0 tok/s in total Mia's own test (her prompt, temperature 0.7, thinking on) Mia's README, 1 request: 47.8 tok/s My Sparks, 1 request: 47.8 tok/s Mia's README, 4 at once: 87.3 tok/s My Sparks, 4 at once: 87.7 tok/s Mia's README, 128K prefill: 1778 tok/s My Sparks, 128K prefi

Posted by Niklas (2.8k followers) 4 h ago · 20 likes · 1.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

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. 31.6k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 00:17 UTC. Full method.