Hackernews posts about Qwen3.5 122B

1. Show HN: Moe-Direct – MoE Models far larger than your RAM, on a consumer desktop (github.com)
   1 points by tmxkzm1925-max 22 days ago | discuss
2. Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers (venturebeat.com)
   461 points by lostmsu 7 months ago | 272 comments
3. Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio (mrzk.io)
   65 points by marzukia 2 months ago | 28 comments
4. Laguna S 2.1:118B-a9B better than Qwen3.5:122B-a10B? So far, yes
   4 points by spottedmarley about 2 months ago | 2 comments
5. Launch HN: IonRouter (YC W26) – High-throughput, low-cost inference (ionrouter.io)
   72 points by vshah1016 6 months ago | 37 comments
6. Launch HN: General Instinct (YC P26) – Frontier models on edge devices
   63 points by guanming0717 4 months ago | 16 comments
7. Show HN: NVFP4 on Desktop Blackwell – 122B MoE on a Single RTX PRO 6000 31 tok/s
   2 points by jcartu 7 months ago | discuss
8. Show HN: An experiment in giving coding agents long-term memory
   1 points by yacc2 6 months ago | 1 comments
9. I'd Rule the World
   1 points by spottedmarley 2 months ago | discuss
10. Ask HN: What benchmarks do you trust most when comparing large LLMs?
    1 points by QubridAI 6 months ago | discuss