New best local model for y'all
16GB-64GB rejoice, the chosen one has arrived.
huggingface.co/Qwen/Qwen3.6-…
cool to see @NousResearch integrate with open source hard.
been running evolution loops for a few weeks with m2.7 in the hermes harness, tool calling improvements are coming along nicely
Capable agents are the result of co-evolution between models and harnesses.
We've been working with @NousResearch to ensure that M2.7 x Hermes Agent provides a top-tier experience for users. Hermes’s self-improving loop brings out the best in M2.7 through real usage.
We are also launching MaxHermes, a cloud-hosted and managed version of Hermes in @MiniMaxAgent (No terminal setup, no config)
If you’re already running Hermes locally, you can now give you agent a partner in the cloud with MaxHermes.
The path to AGI is shorter with good company.
@NousResearch 🤝 @MiniMax_AI
63
love me some cache
Claude Code's compaction engine in one sentence:
Three tiers of cleanup before every API call, LLM summarization dead last, and every decision shaped by one constraint – cache hits are everything.
barazany.dev/blog/claude-cod…
1
46












