Remix.run Logo
wesammikhail 3 hours ago

you'd be surprised how good small models have gotten. Size of the model isnt all that matters.

freedomben 3 hours ago | parent | next [-]

Plus you can control thinking time a lot more, so when Anthropic lobotomizes Opus on you...

verdverm 3 hours ago | parent | prev | next [-]

My experience with qwen-3.6:35B-A3B reinforces this, gonna give this a spin when unsloth has quants available

Gemini flash was just as good as pro for most tasks with good prompts, tools, and context. Gemma 4 was nearly as good as flash and Qwen 3.6 appears to be even better.

cassianoleal 3 hours ago | parent [-]

> when unsloth has quants available

https://huggingface.co/unsloth/Qwen3.6-27B-GGUF

verdverm 3 hours ago | parent [-]

That was quick (compared to the 1T Kimi-2.6, not surprising)

danielhanchen 2 hours ago | parent [-]

Haha :) We had some issues with Kimi-2.6 since it was int4 and we were investigating how to handle it :)

dudefeliciano 2 hours ago | parent | prev [-]

> Size of the model isnt all that matters.

What matters is the motion in the tokens