You can make your own NVFP4 quant now.
This is a dev post classified by AGK Intelligence as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
You can make your own NVFP4 quant now. Download the base weights, point your coding agent at an NVFP4 release you already run and trust, and tell it to quantize the same way. It doesn't take long. It's however not easy to know if it's a good quant! Benchmarks barely help. When comparing multiple 4bit Qwen3.8 27B quants, they often land within 1/2 points of BF16 on task accuracy. What they differ on KL divergence against the BF16 model, on speed, and on behavior: the NVFP4 ones tend to fall into reasoning loops. The tooling leads to issues too. A crashed vLLM eval run on Blackwell can sti
Posted by netrunner (8.3k followers) 56 min ago · 16 likes · 544 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- dsh-superagent: — @arjunkocher
- Run AI inside your Apple app — without routing every prompt through a cloud API. — @DanKornas
- Your local and cloud LLMs don’t need separate chat apps. — @DanKornas
- 想给文章配表情包，脑子里知道要那种「可爱」的反应表情，真去搜的时候，翻好几页也找不到贴切的。 — @GitHub_Daily
- Run an LLM in your Flutter app — without an inference server. — @DanKornas
- GPT-6.1 Terra vs Kimi K3.1 Pro for computer use. — @coastyai
- Your coding agent shouldn’t keep suggesting the approach your team already rejected. — @DanKornas
- Gorgon Halo + DeepSeek V4.1-Flash-1017 + Maya — @PeasantSmith
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, 8.9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-01 02:27 UTC. Full method.