Apache License 2.0
Read the Portuguese translation →
Mentioned in
Section titled “Mentioned in”- CLM-8B vs Jev: What the 9× Speed Demo Actually Shows
- CLI-Anything: Turn ANY App into a CLI for Claude Code & Codex (GIMP, Blender, LibreOffice & More!)
- Qwen4 released
- The Tiny TTS Everyone Loved Isn’t Tiny Anymore (KittenTTS 2)
- I Ran IBM’s New 8B Model in 6GB. Here’s the Catch
- Audio8 ASR Infinite: 89% Wrong vs 6% Wrong, Same Audio
- Amos 1 Small: 69.5% Accurate, Zero Tokens, 5 GB VRAM
- Can’t believe a 2B Strands Decider Local Models Beats Jev
- Julia: 144M Parameters, Picks Answers in 44 ms on a CPU (vs Jev)
- Edge0 35B Tested: 0 Tokens on a 4090, 187 tok/s the Normal Way
- A 34 MB Turkish Text-to-Speech Model: I Tested It on My Laptop
- AWESOME or Overhyped? OXR Document Parsing, Tested With My Own Ugly PDFs
- 12B Coding Model on an 8GB Laptop GPU? I Tested It
- Hy-Memory-30B-A3B + Hy Memory: Local Memory Writer for AI Agents
- Bilibili’s New Translation Model Runs on My 8GB Laptop - I Tested the Memes
- 100% Open Image Model Lets You Place Text With JSON
- Reflection Beam and Cohere North 2: Open Weights vs Locked Down AI
- This speech-to-text model of just 16.9 MB .. crazy
- I Got Real Speech Recognition Running on a $10 Chip (Whistle)
- Skill issue: stop deploying vision language models, use them with Skills — Merve Noyan, Hugging Face
- Laya : Bye TypeSafe Jev AI
- Someone open-sourced Photoshop in Rust: I installed it on my laptop
- Kolibri Has Landed: A Sovereign Open-Weight Model from Germany
- ZDTaichu5.0-9B Local Test: Great Tool Calling, Weak Screenshots
- Large clusters for small models — Daniel Svonava, Superlinked
- Lift by Datalab: 90.2% Accuracy, 3x Faster… and the Number They Left Out
- Google’s AI Rewrites Its Own REVOLUTIONARY Harness (Harness²)
- This Tiny 2B AI vs Claude Code’s Token Bill (Real Test)
- Recursive Flint: This OPEN Local Coding Model is CRAZY! (Tested with Pi, OpenCode & PandaCode)
- Limite 1B Violetto: A Tiny Math Specialist, Tested Locally
- Saluki 27B: a 54 GB model squeezed into 7.89 GB (88 vs 84 on tool calling)
- MiniCPM-V 4.7 35B-A3B Tested Locally: OCR, SQL, Physics and Coding
Related
Section titled “Related”Hugging Face, RunPod, vLLM, PyTorch, llama.cpp, Qwen3.5 9B, Whisper, LibriSpeech, RTX 4090, Ollama, TypeSafe, Jev