Hackernews posts about Qwen3

1. Qwen3.6-Plus: Towards real world agents (qwen.ai)
   593 points by pretext 7 days ago | 213 comments
2. MacBook M5 Pro and Qwen3.5 = Local AI Security System (www.sharpai.org)
   173 points by aegis_camera 20 days ago | 152 comments
3. Qwen-3.6-Plus is the first model to break 1T tokens processed in a day (twitter.com)
   59 points by Alifatisk 3 days ago | 23 comments
4. Qwen3.6-Plus: Towards Real World Agents (qwen.ai)
   21 points by meetpateltech 7 days ago | 4 comments
5. Qwen3.5-Omni (qwen.ai)
   21 points by meetpateltech 10 days ago | discuss
6. Show HN: llamafile 0.10.0 rebuilt, Qwen3.5, lfm2, Anthropic API (blog.mozilla.ai)
   7 points by mzlaai 20 days ago | discuss
7. Qwen 3.6 Free (openrouter.ai)
   5 points by Flere-Imsaho 4 days ago | discuss
8. Qwen 3.6 Plus Preview Available for Free for a Limited Time (twitter.com)
   5 points by mirzap 9 days ago | discuss
9. Show HN: I ran Qwen3.5 35B on my iPhone at 5.6 tok/SEC (twitter.com)
   4 points by alexintosh 18 days ago | 2 comments
10. Qwen3 512k context via TurboQuant on Mac mini (twitter.com)
    3 points by pow-tac 12 days ago | 1 comments
11. AI on a Budget: Recompiling Llama.cpp for Qwen3.5 Inference on an HP Z440 (jeanbaptistefleury.neocities.org)
    3 points by DAFtwinTurbo 30 days ago | 1 comments
12. Are Local LLMs Good Enough for Vibe Coding? Gemma4-26B-A4B vs. Qwen3.5-35B-A3B (grigio.org)
    3 points by grigio 1 day ago | discuss
13. Unlocking LoRA Moe RL for Qwen3.5 (osmosis.ai)
    3 points by WorldPeas 6 days ago | discuss
14. Show HN: Local video search with Qwen3-VL: no API, runs on Apple Silicon, GPUs (github.com)
    3 points by sohamrj 10 days ago | discuss
15. 1M Tokens/s: Scaling Qwen 3.5 27B on 96 B200 GPUs with vLLM (medium.com)
    3 points by m4r1k 13 days ago | discuss
16. 9B parameter coding agent model fine-tuned on top of Qwen3.5-9B (huggingface.co)
    3 points by brainless 27 days ago | discuss
17. Extracting System Prompt and Model Identity from Telegram's AI. It's Qwen 3.5 (medium.com)
    2 points by armalko 5 days ago | discuss
18. Qwen3.5-Omni: Scaling Up, Toward Native Omni-Modal AGI (qwen.ai)
    2 points by maxloh 9 days ago | discuss
19. Run Qwen 3.5 Locally with Claude Code (gist.github.com)
    2 points by lastdong 16 days ago | discuss
20. Teaching Qwen3-4B to Trade: From Hold-Collapse to +9.4% Returns (sabareesh.com)
    2 points by sabareesh 26 days ago | discuss
21. Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs (dnhkng.github.io)
    495 points by dnhkng 30 days ago | 126 comments
22. Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon (github.com)
    240 points by sanchitmonga22 30 days ago | 153 comments
23. Launch HN: IonRouter (YC W26) – High-throughput, low-cost inference (ionrouter.io)
    72 points by vshah1016 28 days ago | 37 comments
24. Show HN: I built a free CharacterAI that runs locally (github.com)
    8 points by akadeb 15 days ago | 4 comments
25. Tell HN: Llamacpp now supports unified system RAM offloading on Linux
    6 points by dabockster 15 days ago | discuss
26. Show HN: On-device meeting transcription for your Mac
    6 points by paynedigital 22 days ago | discuss
27. Show HN: Smart glasses that tell me when to stop pouring (github.com)
    5 points by tash_2s 24 days ago | 7 comments
28. Show HN: LLMadness – March Madness Model Evals (llmadness.com)
    5 points by rjkeck2 21 days ago | 2 comments
29. Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com)
    5 points by GreenGames about 16 hours ago | 1 comments
30. Show HN: Pre-training, fine-tuning, and evals platform (www.oumi.ai)
    4 points by oli_kitty 6 days ago | discuss