MiniMax M3.1 Flash Gets 2-Bit GGUF Support via Unsloth
Unsloth released Dynamic GGUFs for MiniMax M3.1 Flash, compressing the 428B MoE model to a 143.9GB 2-bit footprint with 91.5% top-1 token agreement across seven…
Unsloth released Dynamic GGUFs for MiniMax M3.1 Flash, compressing the 428B MoE model to a 143.9GB 2-bit footprint with 91.5% top-1 token agreement across seven…
Cline Desktop v0.0.49 lets users install and manage local models via Ollama or LM Studio, with hardware-based model recommendations, and adds in-chat review of…
LiteLLM announced day-0 support for GPT-6.1 Terra, a computer-use model priced at $1/$5 per 1M tokens, 50% below GPT-5.6 Terra, with claims of matching GPT-6 As…
Papers with Code, a widely used index linking research papers to code, is now open-source under the Apache 2.0 license, with an invitation for community collabo…
OpenAI has released GPT-6.1 Terra, a model that is significantly better at writing, personality, and nuanced understanding of requests, with strong computer use…
Cursor released an Agent SDK that lets developers define agents as code, with prompts written in Markdown and tools in TypeScript, deployable on Cursor's hosted…
OpenAI's GPT-6.1 Terra is now available on OpenRouter, matching GPT-6 Astra on Agents' Last Exam at one-tenth the price per token and finishing tasks over 3x fa…
Requesty now offers OpenAI's GPT-6.1 Terra, a computer-use model priced well below GPT-5.6 Terra across input, output, and cached input tokens.
OpenAI launched GPT-6.1 Terra, a fast and efficient model with sharper visual reasoning, precise computer use, and more natural writing, rolling out to Plus, Pr…
OpenAI launched GPT-6.1 Terra, a model for computer use that outperforms GPT-5.6 Terra on Agents' Last Exam, matches GPT-6 Astra at one-tenth the price per toke…