Qwen 3.6

1. Do Qwen 3.6 27B quantizations break the pelican? (quesma.com via hn)

   +3 7w qwen

   We tested Qwen3.6 27B quantizations by Unsloth on Hugging Face, with pelicans on bikes, gears, Terminal-Bench 2.1, and AIME-120.

2. Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090 (www.gilesthomas.com via hn)

   +2 8w moeqwen

   Benchmarking Qwen 3.6 35B MoE (3B active) on an RTX 3090 I mentioned I'd got a second RTX 3090 on a group chat, and a friend said: I know this is not really your thing... but let me know how quickly it runs Qwen 3.6 35bn MoE.

3. Pi and Qwen 3.6 went rogue and fixed one of my Rust crates (medium.com via hn)

   +2 8w qwen

   could not extract summary

← all threads