Hackernews posts about Qwen 3

1. Qwen3.6-35B-A3B: Agentic coding power, now open to all (qwen.ai)
   1274 points by cmitsakis 20 days ago | 532 comments
2. Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model (qwen.ai)
   993 points by mfiguiere 14 days ago | 458 comments
3. Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving (qwen.ai)
   705 points by mfiguiere 16 days ago | 377 comments
4. Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7 (simonwillison.net)
   463 points by simonw 20 days ago | 97 comments
5. We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com)
   165 points by GreenGames 16 days ago | 52 comments
6. Qwen/Qwen3.6-27B · Hugging Face (huggingface.co)
   41 points by cgeier 14 days ago | 6 comments
7. Alibaba open-sources Qwen3.6-35B-A3B, a 35B MoE model with 3B active parameters (huggingface.co)
   10 points by steveharing1 20 days ago | discuss
8. Qwen3.5 50% expert reduction success
   7 points by JThomas-CoE 20 days ago | 2 comments
9. Qwen3.5-Omni Technical Report (arxiv.org)
   7 points by gmays 14 days ago | discuss
10. Post-trained Qwen3-Coder with a debugger: 70% → 89% solve rate, 59% fewer turns (twitter.com)
    6 points by moofeez 8 days ago | 1 comments
11. Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090 (github.com)
    5 points by thc1006 16 days ago | 2 comments
12. Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model (simonwillison.net)
    5 points by gmays 9 days ago | 1 comments
13. Qwen3.6-35B-A3B draws a better pelican than Opus 4.7 (twitter.com)
    5 points by armcat 20 days ago | discuss
14. Qwen releases Qwen3-Embedding-0.6B (huggingface.co)
    4 points by arabicalories 17 days ago | 3 comments
15. Show HN: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant
    4 points by freakynit 19 days ago | 2 comments
16. I wrote a custom CUDA inference engine to run Qwen3.5-27B on $130 mining cards (news.ycombinator.com)
    4 points by Haru-neo 4 days ago | 1 comments
17. Qwen-Scope: Official Sparse Autoencoders (SAEs) for Qwen 3.5 Models (qwen.ai)
    4 points by embedding-shape 6 days ago | 1 comments
18. Running Qwen 3.6 35B-A3B-4B on MacBook Pro M5 64GB with tools (www.youtube.com)
    4 points by elvean 17 days ago | 1 comments
19. Messy Model Bench Tests; Qwen3.6-27B vs. Coder-Next (github.com)
    4 points by seemaze 3 days ago | discuss
20. Asking Qwen3.5-9B, running on 16GB VRAM, to exploit old Windows machines (thepatrickfisher.com)
    3 points by sqeak 12 days ago | 3 comments
21. Show HN: Qwen Lens Studio – multimodal app on Qwen3.6-35B-A3B, runs on Ollama (github.com)
    3 points by vijgaurav 14 days ago | 1 comments
22. Qwen3.6-35B-A3B：Now Open-Source (twitter.com)
    3 points by alexellisuk 20 days ago | 1 comments
23. Locally Uncensored v2.3.3 – local AI with Qwen3.6 and remote access (github.com)
    3 points by PurpleDoubleD 20 days ago | discuss
24. I swept all 667 layer duplication configs for Qwen3-4B on 1x RTX 3090 (austinsnerdythings.com)
    3 points by auspiv 21 days ago | discuss
25. Qwen 3.5 Small – on-device multimodal models – Alibaba / Qwen (ai-tldr.dev)
    3 points by ArielSh 22 days ago | discuss
26. Are Local LLMs Good Enough for Vibe Coding? Gemma4-26B-A4B vs. Qwen3.5-35B-A3B (grigio.org)
    3 points by grigio 29 days ago | discuss
27. Moss-Audio: an open-source audio understanding fine-tune of Qwen3 (github.com)
    2 points by subhobroto 6 days ago | 1 comments
28. Show HN: I Added Support for Qwen3-ASR and Qwen3 ForcedAligner in WhisperX (github.com)
    2 points by mahfouz22 22 days ago | 1 comments
29. Local Harness Benchmark: Pi Coding Agent vs. OpenCode with Qwen3.6 35B A3B (grigio.org)
    2 points by grigio 2 days ago | discuss
30. Qwen 3.6 27B SAE (huggingface.co)
    2 points by caiovicentino 6 days ago | discuss