You can run a uncensored Model locally on Phone in 1GB.
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.
You can run a uncensored Model locally on Phone in 1GB. New LFM3-1.7B the refusal rate from 87% to 3% while keeping the same capabilities. - 1.7B parameters - 256K context - 1 GB at 4-bit - Strong tool-calling & agent performance - https://huggingface.co/orcarouter/LFM3-1.7B-abliterated
Posted by Md Ismail Šojal 🕷️ (64.7k followers) 41 min ago · 2 likes · 434 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: lfm3-1.7b-abliterated, deepseek-v4.1-flash-1017-uncensored-gsq-rco-gguf.
More dev work like this
- 想让 AI Agent 不只是会聊天，还能主动获取全球各类实时信息？可以看看这个开源项目。 — @bkdgiffug
- 🔥 @cfontes got the full 753B GLM‑5.3 generating code at 73.6 tokens/sec on four DGX… — @ViC305
- We're hosting another Physical AI Hack this weekend, November 7–8 at @fdotinc in San… — @IsaacSin12
- Stop making your coding agent relearn the same project rules. — @DanKornas
- TRENDING 📈 @paraschopra used Claude Code to predict a live webcam's location from the… — @thestartpod
- 一个人开公司，团队居然已经有人帮你配齐了？ — @bkdgiffug
- It's getting colder and colder here, my fav time of the year, Christmas is almost here. — @ItsmeAjayKV
- AI products can look simple from the outside: a user prompt goes in, and an answer comes… — @freeCodeCamp
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. 31.3k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 02:19 UTC. Full method.