PulseAugur
LIVE 08:28:13
research · [2 sources] ·
0
research

Poolside AI releases open-weight agentic coding models Laguna XS.2 and M.1

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Poolside AI has launched two new open-weight agentic coding models, Laguna XS.2 and M.1. The models achieved impressive scores on the SWE-bench Verified benchmark, with M.1 reaching 72.5% and XS.2 reaching 68.2%. The XS.2 model, a 33-billion parameter model, is notable for its ability to run locally on consumer hardware with 36GB of RAM, making advanced coding assistance more accessible. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Provides accessible, locally runnable agentic coding tools, potentially lowering barriers for developers.

RANK_REASON Release of open-weight coding models with benchmark results.

Read on Mastodon — fosstodon.org →

COVERAGE [2]

  1. Mastodon — fosstodon.org TIER_1 · [email protected] ·

    Poolside AI has released Laguna XS.2 and M.1, open-weight agentic coding models that achieve 68.2% and 72.5% on SWE-bench Verified respectively. The XS.2 model

    Poolside AI has released Laguna XS.2 and M.1, open-weight agentic coding models that achieve 68.2% and 72.5% on SWE-bench Verified respectively. The XS.2 model runs locally on a Mac with 36GB RAM. https://www. marktechpost.com/2026/04/28/po olside-ai-introduces-laguna-xs-2-and-m-…

    LINKS marktechpost.com/…/poolside-ai-introduces…
  2. Mastodon — fosstodon.org TIER_1 · [email protected] ·

    American AI startup Poolside has released Laguna XS.2, a free open-source model for local agentic coding. The 33bn-parameter model runs locally on a single GPU,

    American AI startup Poolside has released Laguna XS.2, a free open-source model for local agentic coding. The 33bn-parameter model runs locally on a single GPU, achieving 44.5% on SWE-bench Pro, nearly matching models six times its size. Available via Hugging Face and Ollama. htt…

RELATED ENTITIES

RELATED TOPICS