lmcoleman author hub
What this is A 50% expert pruned poolside/Laguna XS 2.1 https://huggingface.co/poolside/Laguna XS 2.1 33.4B, 256 expert MoE reduced to 17.7B / 128 experts with REAP https://github.com/CerebrasResearch/reap router weighted expert pruning, then quantized with MagicQuant's measured…
Models
11
Downloads
22,226
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.