UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source…
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source Jev-like decision models you can train and run yourself. This new family is based on Qwen3 using the same LoRA + small pointer head technique as before, but scaled up. Out of domain, on data Kev never trained on: Kev-8B 79.6%, Jev 85.7%. • Drop-in TypeSafe System One API; their SDK works with one `base_url` change • Kev-4B serves on a 32 GB Mac in bf16: ~300 ms for five questions, ~40 ms on an H100 • Repeated documents hit a KV cache: 2-2.5x faster • Apache 2.0 License. Kev-4B trains in 40 minutes on one
Posted by Jared Palmer (109.9k followers) 1 h ago · 340 likes · 18.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: kev.
More dev work like this
- you can just make your agent a looper on @Muse if you want — @QuigleyNFT
- Muse Code usage — @Everlier
- Running several AI coding agents? Don’t lose track of the quota each one has left. — @DanKornas
- I'm sharing my latest no-code personal slop experiment, an opinionated ADE. Check it out… — @kcosr
- DeepSeek v4.1 flash made using only Javascript — @cherry_mx_reds
- the next era is not the Claude Code or Codex era. — @0x_rody
- LFG @MiniMax_AI — @u1tra_instinct
- 🌟 Diagram Design Skill🌟 — @bibryam
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 16.1k posts from 4.9k X accounts over the last 21 days, 1.8k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 18:21 UTC. Full method.