Hackernews posts about Qwen 4B

  1. I've tested some local LLMs on prosumer hardware, here are some findings
    7 points by felineflock 28 days ago | discuss
  2. Show HN: Zero downtime embedding model upgrades (github.com)
    6 points by coolArnav 13 days ago | 3 comments
  3. Show HN: An open-weight LLM whose answer/stop decision can be flipped internally (github.com)
    1 points by rayanpal_ 11 days ago | discuss
  4. Training Qwen 4B to Beat Large Models on Work Tasks (neurometric.substack.com)
    16 points by robmay 7 months ago | discuss
  5. Show HN: Dante-Qwen-4B – Curing LLM "Neurosis" with a Divine Comedy Curriculum (huggingface.co)
    5 points by hunterbown 10 months ago | 1 comments
  6. Good Results when training Qwen 3 4B to learn a new domain (www.teachmecoolstuff.com)
    5 points by dev-experiments about 1 month ago | discuss
  7. Show HN: Distilled 0.6B text-to-SQL model (github.com)
    5 points by maciejgryka 8 months ago | discuss
  8. Show HN: An offline first focused agentic CLI application powered by Ollama
    4 points by g023 6 months ago | discuss
  9. Sumi – Open-source voice-to-text with local AI polishing
    2 points by alkd 7 months ago | discuss
  10. Show HN: Promptscout a local prompt enricher for Claude Code (github.com)
    2 points by obsfx 7 months ago | discuss
  11. Qwen3-4B-Thinking-2507 (huggingface.co)
    198 points by IdealeZahlen about 1 year ago | 61 comments
  12. On-device Qwen benchmark: the 4B ties the 9B, and more findings (github.com)
    2 points by thomasblanc 2 months ago | discuss
  13. Show HN: Building a full agentic harness around a 4B model is hard (orvena.app)
    5 points by mehrant about 1 month ago | discuss
  14. Qwen 3.5 9B, 4B models beating 30B, 80B models (huggingface.co)
    2 points by satvikpendem 7 months ago | discuss
  15. Qwen 3.5: 9B, 4B, 2B, 0.8B (huggingface.co)
    7 points by tosh 7 months ago | discuss
  16. Running Qwen 3.6 35B-A3B-4B on MacBook Pro M5 64GB with tools (www.youtube.com)
    4 points by elvean 5 months ago | 1 comments
  17. Show HN: I fine-tuned Qwen 3.5 (0.8B–4B) on a Mac for text-to-SQL – 2B beats 12B (github.com)
    7 points by sciences44 7 months ago | 1 comments
  18. Show HN: Jan-nano, 4B agentic model that outperforms DeepSeek-v3-671B using MCP (twitter.com)
    6 points by emreckartal over 1 year ago | discuss
  19. Is anyone compressing AI models for the 4B people without GPUs or internet?
    3 points by yashpxl 7 months ago | 1 comments
  20. 4B parameter Deep Research model based on Qwen (huggingface.co)
    1 points by sumo43 11 months ago | discuss
  21. Launch HN: RunRL (YC X25) – Reinforcement learning as a service (runrl.com)
    71 points by ag8 about 1 year ago | 22 comments
  22. Show HN: KARMA – An evaluation framework for Medical AI systems (karma.eka.care)
    2 points by k2so about 1 year ago | discuss
  23. Qwen3-4B-Thinking: "This is art–pelicans don't ride bikes " (simonwillison.net)
    4 points by nnx about 1 year ago | discuss
  24. I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090 (austinsnerdythings.com)
    3 points by auspiv 5 months ago | discuss
  25. Qwen3-VL-4B and 8B runs locally on NPU, GPU, and CPU with one SDK (nexa.ai)
    3 points by alanzhuly 11 months ago | discuss
  26. Teaching Qwen3-4B to Trade: From Hold-Collapse to +9.4% Returns (sabareesh.com)
    2 points by sabareesh 6 months ago | discuss
  27. Latest progress helping Qwen3-4B Learn (github.com)
    2 points by kibbyd1985 7 months ago | discuss
  28. Fine‑tuning Qwen3‑4B on a MacBook M1 for customer support (blog.layerx.xyz)
    1 points by felltrifortence 5 months ago | discuss
  29. A fine-tune of Qwen3-4B for use with Cavil for legal text classification (huggingface.co)
    1 points by Tomte about 1 year ago | discuss
  30. Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon (github.com)
    240 points by sanchitmonga22 6 months ago | 153 comments
  31. Launch HN: Cactus (YC S25) – AI inference on smartphones (github.com)
    123 points by HenryNdubuaku about 1 year ago | 63 comments
  32. Show HN: On-device meeting transcription for your Mac
    6 points by paynedigital 6 months ago | discuss
  33. Show HN: Minna – On-device semantic search across your own documents (macOS) (github.com)
    3 points by ActuallyTaylor about 1 month ago | discuss