MiniMax-M3.1-Flash (428B) decodes at 24.0 tok/s on one RTX 5090 plus 92 GiB RAM, and…
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.
MiniMax-M3.1-Flash (428B) decodes at 24.0 tok/s on one RTX 5090 plus 92 GiB RAM, and 18.7 with a 249K prompt RTX 5090, 32 GB, plus 92 GiB RAM Decode, code and prose: 24.0 tok/s Decode, code: 24.4 tok/s Decode, prose: 23.6 tok/s 500 words (code and prose): about 27.5 s First token at 16K: 36.6 s First token at 128K: 465.8 s Decode with a 249K prompt: 18.7 tok/s Project Maya 1.1.50, Maya-XS (93 GB, IQ1_S experts at about 1.6 bpw in RAM and VRAM), DSpark drafts Maya's own installer, recommended answers, nothing edited: 262,144 context on this PC Speed test, median of 2 runs, 512 tokens, tempera
Posted by Niklas (2.8k followers) 1 days ago · 13 likes · 1.8k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Introducing Baseten Grid: gateway, intelligent routing, and guardrails in one layer, so… — @baseten
- Voyager says it’s offering Seedance 2.5 at half Higgsfield’s 720p API price with a… — @StockSavvyShay
- Ok, *this is impressive*: Ricursive Intelligence just released Ripple-65B Preview, an… — @kimmonismus
- A new American open-weights AI model is here! 🇺🇸🔥 — @mark_k
- GPT-QModel v7.9.0 released👇 — @qubitium
- Bring your questions about PyTorch 2.15 to our live Q&A TOMORROW, November 5, at 11 AM PT. — @PyTorch
- Stay connected 🤝 — @HeyGen
- awesome new model from Recursive that punches above it's weight particularly for agentic… — @zainhas
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. 31.4k 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 2026-11-04 20:09 UTC. Full method.