Deals ·
Free GitHub Copilot Pro for verified teachers and OSS maintainers
Verified teachers on GitHub Education and maintainers of popular open-source repositories get Copilot Pro for free. GitHub re-checks eligibility every month.
GitHub
Open-source AI news
Open-weight models, frameworks and community releases.
Business ·
NVIDIA agrees to buy Hugging Face for about $12.9B and pledges to keep it open
NVIDIA announced a deal to acquire Hugging Face for $12.93 billion, and pledged that the hub will stay open, multi-cloud and usable without NVIDIA hardware. Hugging Face hosts…
NVIDIA
Alibaba unveils Qwen3.8-Max, a 2.4T-parameter MoE with open weights to follow
Alibaba unveiled Qwen3.8-Max, a sparse mixture-of-experts model with 2.4 trillion total and about 95B active parameters aimed at coding and 'cowork' agent tasks, and committed to…
Alibaba Qwen
Moonshot opens up Kimi K3, a 2.8T-parameter multimodal MoE model
Moonshot AI published weights for Kimi K3, a 2.8-trillion-parameter mixture-of-experts model with about 104B active parameters, a 1M-token context window and native text, image…
Moonshot AI
Z.ai releases GLM-5.2 open weights with a 1M-token context under MIT
Z.ai released GLM-5.2, a roughly 753B-parameter successor to GLM-5.1 with a 1M-token context window and multiple thinking-effort levels, under an MIT license without regional…
Z.ai
DeepSeek V4 preview drops open weights with a 1M-token context window
DeepSeek published open weights for DeepSeek-V4-Pro (1.6T total, 49B active parameters) and V4-Flash (284B total, 13B active), both with 1M-token context and thinking and…
DeepSeek
Gemma 4 goes Apache 2.0, spanning edge-sized models to a 31B dense model
Google DeepMind released Gemma 4 in four sizes (effective 2B and 4B edge models, a 26B mixture-of-experts and a 31B dense model) under the Apache 2.0 license. The models support…
Mistral Small 4 merges reasoning, vision and coding into one Apache 2.0 model
Mistral Small 4 is a 119B-parameter mixture-of-experts model with about 6B active parameters per token, a 256k context window and image input, released under Apache 2.0. It…
Mistral AI
Qwen3.5 arrives: a 397B open-weight multimodal MoE with a 1M-token context
Alibaba's Qwen team released Qwen3.5-397B-A17B, a mixture-of-experts model with 17B active parameters, a 1M-token context window and native vision-language support, alongside a…
Alibaba Qwen
Z.ai open-sources GLM-5, a 744B MoE model for long-horizon agents, under MIT
Z.ai launched GLM-5, a 744B-parameter mixture-of-experts model with about 40B active parameters, released with open weights under the MIT license. It targets complex systems…
Z.ai
DeepSeek ships V3.2 and a high-compute V3.2-Speciale for hard reasoning
DeepSeek released DeepSeek-V3.2 as its new production model and V3.2-Speciale as a high-compute variant aimed at hard reasoning problems. The release builds on DeepSeek Sparse…
DeepSeek
Kimi K2 Thinking: Moonshot's open trillion-parameter agent model chains tool calls
Moonshot AI released Kimi K2 Thinking, an open-weight trillion-parameter mixture-of-experts model with 32B active parameters, trained to interleave reasoning with tool calls…
Simon Willison