Day-0 support on MLX for Mistral Small 4 Congratulations to the ...
Quick Answer
MistralAI has launched Mistral Small 4, a versatile model featuring 128 experts and 119B parameters, designed for enhanced performance with a 256k context window.
Quick Take
It boasts 40% faster speeds and 3x more throughput, unifying capabilities of previous flagship models under Apache 2.0 licensing.
Key Points
- Mistral Small 4 features 128 experts and 119 billion parameters.
- The model supports a 256k context window for improved reasoning.
- Performance is 40% faster with three times the throughput of predecessors.
- It is the first model to unify capabilities of Mistral's flagship offerings.
- Mistral Small 4 is released under Apache 2.0 licensing.
Article Excerpt
From source RSS / original summary## Post. Day-0 support on MLX for Mistral Small 4🚀 Congratulations to the @MistralAI team on the release. 🔥 Meet Mistral Small 4: One model to do it all. ⚡ 128 experts, 119B total parameters, 256k context window ⚡ Configurable Reasoning ⚡ Apache 2. 0 ⚡ 40% faster, 3x more throughput Our first model to unify the capabilities of our flagship models into a single, versatile model. 1:41 AM · Mar 17, 20266. 9KViews. Don't miss what's happening. People on X are the first to know.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from WebSearch (Tavily)
See more →全球AI芯片峰会，9月上海见！
The 2026 Global AI Chip Summit will take place in Shanghai on September 22-23, focusing on the evolving AI chip landscape, including the shift from training to inference, the rise of diverse chip technologies, and the restructuring of industry competition. Notable speakers include experts from leading universities and companies, discussing advancements in AI chip architecture and applications.