Laguna M.1
Laguna M.1 is a 225B total parameter (23B activated) Mixture-of-Experts model built for agentic coding and long-horizon software engineering. It features a 262,144-token context window, native interleaved reasoning with per-request thinking control, and tool calling support. Achieves 74.6% on SWE-bench Verified and 49.2% on SWE-bench Pro. Apache 2.0 licensed.
- Type
- Coding
- Weights
- Closed
More from poolside
11
-
Laguna S 2.1
Text
Laguna S 2.1 is a 118B parameter Mixture of Experts model with 8B activated parameters per token, built for a…
-
113k DL
Laguna XS 2
Text
Laguna XS.2 is poolside’s open 33B MoE coding model for agentic software work on local machines. It uses 3B a…
-
116k DL
Laguna-M.1
Text
text generation · License apache-2.0 · 115,665 downloads · by poolside
-
104k DL
Laguna-S-2.1-GGUF
Text
626,503 downloads · by poolside
-
414k DL
Laguna-S-2.1-NVFP4
Text
text generation · License openmdw-1.1 · 414,136 downloads · by poolside
-
222k DL
Laguna-XS-2.1-GGUF
Text
text generation · License openmdw-1.1 · 221,766 downloads · by poolside
-
206k DL
Laguna-XS-2.1-NVFP4
Text
text generation · License openmdw-1.1 · 206,171 downloads · by poolside
-
141k DL
Laguna-XS.2
Text
text generation · License apache-2.0 · 140,699 downloads · by poolside
About poolside
1
poolside is a foundation-model company building AI for software engineering. It develops proprietary frontier models (Malibu, Point, and the open-weight Laguna XS.2) plus a full agentic platform — IDE/TUI integrations, multi-agent systems, and connectors — deployed on-prem, in customer VPCs, or in air-gapped environments. Targets large enterprises and the U.S. defense industrial base. Mission stated as building AGI via software engineering as the strategic beachhead.