Heads up: this is not a Kimi K3.1 Pro model you want to run. The README says "expect a…
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.
Heads up: this is not a Kimi K3.1 Pro model you want to run. The README says "expect a large quality regression" and "for smoke tests on fewer GPUs" and that's exactly what you'll get. Not a smart model - just a much smaller model to test kernels. https://huggingface.co/vllm-project/Kimi-K3.1-Pro-pruned75
Posted by Matt Mastracci (11.2k followers) 3 h ago · 2 likes · 262 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: kimi-k3.1-pro-pruned75.
More dev work like this
- We helped @thinkymachines evaluate Inkling 2 Small ahead of today's launch. Here's how… — @mercor
- Technology Behind RAG! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc… — @gp_pulipaka
- alright...it is time. — @RileyRalmuto
- I've taken matters into my own hands with @Apple's Metal. 🔥 — @ashxhart
- Generative AI Risks and Benefits within Human-Machine Teams! #BigData #Analytics… — @gp_pulipaka
- Bi-Directionality in Human-AI Collaborative Systems! #BigData #Analytics #DataScience… — @gp_pulipaka
- Every Agent API effort level now costs less with the same or higher research quality. — @perplexitydevs
- Hermes Agent v0.23.0: The Hearth Release — @NousResearch
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. 31.8k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 23:57 UTC. Full method.