Hackernews posts about 35B

1. Qwen3.6-35B-A3B: Agentic coding power, now open to all (qwen.ai)
   1274 points by cmitsakis 20 days ago | 532 comments
2. Qwen3.6-35B-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
3. 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
4. Qwen3.6-35B-A3B speculative decoding is net-negative on RTX 3090 (github.com)
   5 points by thc1006 16 days ago | 2 comments
5. Qwen3.6-35B-A3B draws a better pelican than Opus 4.7 (twitter.com)
   5 points by armcat 20 days ago | discuss
6. My $600 Mac Mini Runs a 35B AI Model (thoughts.jock.pl)
   4 points by danebalia 23 days ago | 3 comments
7. Show HN: Open Access Qwen3.6-35B-A3B-UD-Q5_K_M with TurboQuant
   4 points by freakynit 20 days ago | 2 comments
8. 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
9. 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
10. Qwen3.6-35B-A3B：Now Open-Source (twitter.com)
    3 points by alexellisuk 20 days ago | 1 comments
11. 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
12. Local Harness Benchmark: Pi Coding Agent vs. OpenCode with Qwen3.6 35B A3B (grigio.org)
    2 points by grigio 3 days ago | discuss
13. Qwen3.6 35B A3B is THE ONE The Local LLM Champ on OpenCode benchmark dashboard [video] (www.youtube.com)
    2 points by grigio 20 days ago | discuss
14. Can I code on my PC? Gemma4 26B A4B vs. Qwen3.6 35B A3B Coding benchmark (grigio.org)
    1 points by grigio 17 days ago | 1 comments
15. Show HN: A new benchmark for testing LLMs for deterministic outputs (interfaze.ai)
    60 points by khurdula 7 days ago | 30 comments
16. Qwen3.5 50% expert reduction success
    7 points by JThomas-CoE 20 days ago | 2 comments
17. Granite 4.1: IBM's 8B Model Matching 32B MoE (firethering.com)
    327 points by steveharing1 7 days ago | 209 comments
18. F-35 is built for the wrong war (warontherocks.com)
    299 points by anjel 16 days ago | 692 comments
19. F-35 Got Hit (www.shatterbelt.co)
    28 points by xrd 28 days ago | 56 comments
20. 10,947 signups, 90 paid, €6,356 in nine years (khanin.info)
    11 points by daniilkhanin 8 days ago | 2 comments
21. F-35s Quarterbacking Drones Seen as Gateway to USMC's 6th Gen Fighter (www.twz.com)
    11 points by breve 14 days ago | 1 comments
22. Native Raspberry Pi 3B version of the Oberon System 3 (github.com)
    9 points by HotGarbage 25 days ago | discuss
23. Show HN: Flint – A 30B model fine-tuned for less repetition (springboards.ai)
    6 points by thmsmxwll 21 days ago | 2 comments
24. Show HN: We trained a 32B model to beat Opus 4 at credit card optimization (huggingface.co)
    6 points by dimberman 16 days ago | discuss
25. Show HN: Codemaxxed – 350M+ LOC and a GitHub cease and desist (github.com)
    5 points by jshchnz 19 days ago | 2 comments
26. Distinguishing Malicious from Vulnerable: 2,354 Popular ClawHub Skills Analysed (trent.ai)
    5 points by JulienBrouchier 21 days ago | 1 comments
27. Open-sourced the skills behind 353K views and 5,300 signups for a YC company (github.com)
    4 points by devgod 8 days ago | 2 comments
28. Linux averaging ~350 CVEs per day (crib.social)
    4 points by gslepak 5 days ago | discuss
29. Making a 3B Robot Policy Faster (www.hapticlabs.ai)
    4 points by ibero 13 days ago | discuss
30. HP 3585A spectrum analyzer teardown (7400.me)
    3 points by picture 4 days ago | discuss