Laguna (XS.2)
PulseAugur coverage of Laguna (XS.2) — every cluster mentioning Laguna (XS.2) across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
ik_llama.cpp adds support for Laguna M.1 GGUF model
A pull request has been submitted to the ik_llama.cpp repository to add support for the Laguna M.1 GGUF model. This update, identified as pull request #2003, aims to integrate the new model format into the existing code…
-
Poolside releases Laguna M.1 open-source AI model
American AI company Poolside has released the weights for its Laguna M.1 model, making it available as an open-source model under the Apache 2.0 license. This model, previously available only via API, boasts a 256K cont…
-
AI model pricing sees major shifts; Z.ai cuts costs, new models emerge
AI pricing is seeing significant shifts, with Z.ai notably reducing its GLM 5.2 prompt and completion prices, offering substantial savings for high-volume users. Other providers like MoonshotAI and Qwen have also adjust…
-
LLM Architectures Innovate with KV Sharing, Compressed Attention for Long Context
Recent advancements in Large Language Model (LLM) architectures are focusing on improving efficiency for long context windows, addressing resource constraints like KV cache size and memory bandwidth. Techniques such as …
-
LLM agents struggle to patch security bugs, leaving vulnerabilities open
A new benchmark, CVE-Bench, was developed to evaluate LLM agents' ability to patch security vulnerabilities in Python projects. Across 18 projects and 20 real-world CVEs, the best performing models achieved only a 50% s…
-
Laguna (XS.2) Model Integrated into Llama.cpp for Local Use
A developer has integrated the Laguna (XS.2) model into the Llama.cpp framework, enabling its use on local hardware. This implementation allows users to run the model efficiently, leveraging the capabilities of Llama.cp…
-
Laguna M.1/XS.2 Models Debut for Agentic Coding Tasks
Researchers have introduced Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models designed for long-horizon, agentic coding tasks. Laguna M.1 features 225.8 billion total parameters with 23.4 billion acti…
-
LLM Architectures Innovate for Long-Context Efficiency
Sebastian Raschka's analysis highlights recent architectural innovations in open-weight LLMs aimed at improving long-context efficiency. Key developments include KV sharing and per-layer embeddings in Google's Gemma 4 m…
-
Poolside AI releases open-weight agentic coding models Laguna XS.2 and M.1
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…
-
🚀 New Ollama Model Release! 🚀 Model: nemotron3 🔗 https://ollama.com/library/nemotron3 # Ollama # AI # LLM # mcpo
Ollama has released version v0.22.1, which includes updates to the Gemma 4 renderer for improved thinking and tool-calling capabilities. This release also ensures model recommendations update without requiring a full Ol…
-
Poolside AI releases open-weight Laguna XS.2 and M.1 coding models
Poolside AI has released two new agentic coding models, Laguna M.1 and Laguna XS.2, along with their agent training and operation runtime. Laguna M.1 is a large Mixture of Experts (MoE) model trained on 30T tokens using…