Every lab should ship its own 4bit weights.
This is a AI post classified by AGK Intelligence as Open & local models (an opinion), kept by the AI Radar because it carries real work, not commentary.
Every lab should ship its own 4bit weights. @liquidai just did it for LFM3, releasing an official NVFP4 for the 1.7B and a VL-2B. If labs do the quants like in this case, there's one version everyone runs. So when something's off, everyone's reporting on the same weights. https://huggingface.co/LiquidAI/LFM3-1.7B-NVFP4
Posted by netrunner (8.4k followers) 2 h ago · 12 likes · 616 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: lfm3-1.7b-nvfp4.
More AI work like this
- Qwen3.8 27B QSAではこのアーキテクチャを使い、速度低下を大幅に軽減しています — @_ryu15_
- Meet Mistral Small 3.2 24B Instruct, now in a heretic GGUF edition. This uncensored,… — @HuggingModels
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Qwen 4 Unknown Preview bee on a sunflower. — @loktar00
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. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.