Mixture-of-Experts
All articles
10 total
DeepSeek Updated
DeepSeek is a Chinese AI lab known for open-weight large language models …
Added 29 Jun
·
Upd 25 Sep
·13 min
Mixture of Experts Updated
Routing Queries to Specialist Sub-Networks
Frameworks
Added 28 Mar
·
Upd 25 Sep
·4 min
DeepSeek-V4.1-Flash: A New Architecture, MIT Weights, and Lower Flash Prices New
DeepSeek released DeepSeek-V4.1-Flash on 10 September 2026. It is a …
News
Added 10 Sep
·
Upd 25 Sep
·5 min
Cohere Command A+ Ships Under Apache 2.0
Cohere announced Command A+ on 20 May 2026, its first Mixture-of-Experts …
News
Added 6 Jul
·
Upd 6 Jul
·2 min
DeepSeek Releases V4 Open-Weight Models
On 24 April 2026 DeepSeek released a preview of DeepSeek-V4-Pro and …
News
Added 6 Jul
·
Upd 6 Jul
·2 min
Gemma 4 Lands on Amazon Bedrock
Google DeepMind's open Gemma 4 family is now available on Amazon Bedrock …
News
Added 15 Jun
·
Upd 16 Jun
·3 min
Mistral Small 4 Unifies Reasoning, Vision, and Coding
Mistral AI announced Mistral Small 4 on 16 March 2026 under Apache 2.0, …
News
Added 6 Jul
·
Upd 6 Jul
·2 min
Moonshot AI Announces Kimi K3, a 2.8-Trillion-Parameter Open-Weight Flagship
Moonshot AI announced Kimi K3, a 2.8T-parameter mixture-of-experts model …
News
Added 17 Jul
·
Upd 17 Jul
·3 min
NVIDIA Ships the Nemotron 3 Open-Weight Model Family
Across GTC 2026 and the following months NVIDIA released the Nemotron 3 …
News
Added 4 Jun
·
Upd 13 Jul
·3 min
Thinking Machines Lab Releases Inkling, Its First Model, as Open Weights
Thinking Machines Lab released Inkling, its first model: a …
News
Added 17 Jul
·
Upd 17 Jul
·2 min
Work with Linda Mohamed, AWS Community Hero