Hackernews posts about Qwen 3

1. How to run Qwen 3.5 locally (unsloth.ai)
   490 points by Curiositry 13 days ago | 168 comments
2. Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers (venturebeat.com)
   461 points by lostmsu 20 days ago | 272 comments
3. Qwen3.5 Fine-Tuning Guide (unsloth.ai)
   416 points by bilsbie 17 days ago | 108 comments
4. MacBook M5 Pro and Qwen3.5 = Local AI Security System (www.sharpai.org)
   156 points by aegis_camera about 13 hours ago | 146 comments
5. Qwen 3.5 small models out (huggingface.co)
   18 points by andhuman 24 days ago | 3 comments
6. Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally (twitter.com)
   12 points by m-hodges 2 days ago | discuss
7. The Qwen 3.5 Small Model Series (twitter.com)
   11 points by armcat 19 days ago | 2 comments
8. Qwen3.5 Small: 0.8B, 2B, 4B, 9B Released (huggingface.co)
   10 points by syx 19 days ago | 5 comments
9. 2x Qwen 3.5 on M1 Mac: 9B builds a bot, 0.8B runs it (advanced-stack.com)
   10 points by advanced-stack 18 days ago | 4 comments
10. 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 16 days ago | 1 comments
11. Show HN: llamafile 0.10.0 rebuilt, Qwen3.5, lfm2, Anthropic API (blog.mozilla.ai)
    7 points by mzlaai 1 day ago | discuss
12. Qwen 3.5: 9B, 4B, 2B, 0.8B (huggingface.co)
    7 points by tosh 19 days ago | discuss
13. Qwen 3.5 Medium Model Series (twitter.com)
    7 points by tosh 25 days ago | discuss
14. Show HN: Qwen 3.5 running on a $300 Android phone – on-device, open source (github.com)
    6 points by ali_chherawalla 17 days ago | 10 comments
15. Qwen 3.5: small models with impressive performance (twitter.com)
    6 points by moondistance 18 days ago | discuss
16. Qwen3.5 GGUF Benchmarks (unsloth.ai)
    5 points by tosh 21 days ago | discuss
17. Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled (huggingface.co)
    4 points by simonpure 17 days ago | 2 comments
18. Open-source voice cloning app using Qwen3-TTS (github.com)
    4 points by angelmm 30 days ago | discuss
19. AI on a Budget: Recompiling Llama.cpp for Qwen3.5 Inference on an HP Z440 (jeanbaptistefleury.neocities.org)
    3 points by DAFtwinTurbo 11 days ago | 1 comments
20. 9B parameter coding agent model fine-tuned on top of Qwen3.5-9B (huggingface.co)
    3 points by brainless 8 days ago | discuss
21. Qwen3.5-35B-A3B (huggingface.co)
    3 points by throwaway2027 21 days ago | discuss
22. Qwen3.5-35B – 16GB GPU – 100T/s with 120K context AND vision enabled (github.com)
    2 points by willfinger 14 days ago | 2 comments
23. Migrating Elderly Care AI from Qwen 3 to 3.5 on Apple Silicon – 14x Latency Fix (medium.com)
    2 points by asqpl 18 days ago | 1 comments
24. Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally with low RAM (simonwillison.net)
    2 points by walterbell 1 day ago | discuss
25. Autoresearching Apple's "LLM in a Flash" to run Qwen 397B locally (twitter.com)
    2 points by rzk 2 days ago | discuss
26. Teaching Qwen3-4B to Trade: From Hold-Collapse to +9.4% Returns (sabareesh.com)
    2 points by sabareesh 7 days ago | discuss
27. Show HN: I made Qwen3.5-4B 13% smarter by compressing it to 4-bit (huggingface.co)
    2 points by singularity_max 12 days ago | discuss
28. According to benchmarks Qwen3.5 4B is as good as GPT 4o (twitter.com)
    2 points by dataminer 13 days ago | discuss
29. Show HN: EdgeDox – Offline document AI on Android using Qwen3.5-0.8B (play.google.com)
    2 points by cyberfly-labs 14 days ago | discuss
30. Qwen3-ASR-Swift (github.com)
    2 points by handfuloflight 16 days ago | discuss