New blocks

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Devstral is an agentic LLM for software engineering tasks built under a collaboration between Mistral AI and All Hands AI 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. https://huggingface.co/mistralai/Devstral-Small-2507_gguf

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

State-of-the-art code LLM with 32B parameters, matching GPT-4o coding abilities. Enhanced code generation, reasoning and fixing capabilities. https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct-GGUF

Llama 4 Scout is a 17B parameter multimodal AI model with 16 experts, offering industry-leading text and image understanding. https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct

django-simple-history docs

ia

111

The Convex Backend Rules Sourced from https://docs.convex.dev/ai/using-github-copilot#add-convex-instructions

The Convex MCP Server More details: https://docs.convex.dev/ai/convex-mcp-server