Xiaomi have distilled MiMo V2.6 into Qwen3.5-9B and have introduced an MTP head into it…
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Xiaomi have distilled MiMo V2.6 into Qwen3.5-9B and have introduced an MTP head into it along with support for preserve_thinking. might be worth checking out if you've been looking for a good, smaller dense model. https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B ty @XiaomiTech_
Posted by shaun (3.1k followers) 1 h ago · 8 likes · 400 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: mimo-v2.6-distill-qwen-9b.
More AI work like this
- Qwen 4 is coming soon : — @0x0SojalSec
- Meet Lanni-ni/hard_2gram_pile_2layer, a text-generation transformer with a twist: it's a… — @HuggingModels
- Introducing Hotdog-27B, a specialized bipartite classifier. — @michael_chomsky
- update on the same bundle. a new prefill kernel landed in the prismml fork this morning,… — @sudoingX
- We got new image gen model releases from @AntLingAGI — @ItsmeAjayKV
- Meet a 100M parameter transformer trained on the BabyLM dataset. It is a text generation… — @HuggingModels
- Just launched my usual Qwen 3.8 27B configs and, for a brief moment, couldn't understand… — @Anbeeld
- We’re open-sourcing the Ming-Image-0.1-Design family: — @AntLingAGI
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.1k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 20:50 UTC. Full method.