News for hackers. Stuff that matters.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by CamperBob2 on Saturday February 28, 2026 @06:56PM (#47201915)
Try the 27B dense model. It will likely do much better than the 35b MoE with only 3B active experts.

Also, performance on research-y questions isn't always a good indicator of how the model will do for code generation or agent orchestration.

Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by regularfry on Sunday March 01, 2026 @09:05AM (#47206780)
Currently sat waiting for the unsloth fixed quants to drop, but I'm on the edge of my seat for this.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by Balinares on Sunday March 01, 2026 @04:56PM (#47211124)
Wait, didn't they drop like two days ago?
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by regularfry on Monday March 02, 2026 @10:22AM (#47219120)
The 35b did but not the 27b. Looks like the latter has been updated in the last half hour.
Re:Qwen3.5 122B and 35B models offer Sonnet 4.5 performance ... by Balinares on Monday March 02, 2026 @05:22PM (#47225015)
Neat! Thanks for correcting me there. I'll go and take a look.