Hackernews posts about Qwen3.5 122B

1. 01
   

   newShow HN: LoRA over GGUF – Train Qwen3.8-Flash-Next in 40G VRAMgithub.com

   ▲ 1woctordho28ddiscusssavesaved
2. 02
   

   newQwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computersventurebeat.com

   ▲ 461lostmsu252d💬 272savesaved
3. 03
   

   newFixed three bugs that made Qwen3.5-122B a daily driver on Mac Studiomrzk.io

   ▲ 65marzukia119d💬 28savesaved
4. 04
   

   newLaguna S 2.1:118B-a9B better than Qwen3.5:122B-a10B? So far, yes

   ▲ 4spottedmarley93d💬 2savesaved
5. 05
   

   newLaunch HN: IonRouter (YC W26) – High-throughput, low-cost inferenceionrouter.io

   ▲ 72vshah1016240d💬 37savesaved
6. 06
   

   newLaunch HN: General Instinct (YC P26) – Frontier models on edge devices

   ▲ 63guanming0717155d💬 16savesaved
7. 07
   

   newShow HN: NVFP4 on Desktop Blackwell – 122B MoE on a Single RTX PRO 6000 31 tok/s

   ▲ 2jcartu243ddiscusssavesaved
8. 08
   

   newShow HN: An experiment in giving coding agents long-term memory

   ▲ 1yacc2238d💬 1savesaved
9. 09
   

   newShow HN: Moe-Direct – MoE Models far larger than your RAM, on a consumer desktopgithub.com

   ▲ 1tmxkzm1925-max70ddiscusssavesaved
10. 10
    

    newI'd Rule the World

    ▲ 1spottedmarley115ddiscusssavesaved
11. 11
    

    newAsk HN: What benchmarks do you trust most when comparing large LLMs?

    ▲ 1QubridAI240ddiscusssavesaved

· edit