TLDRocket
Sign in

Mixture-of-Experts

43 summarised stories about Mixture-of-Experts, each linking back to the original source. Browse all topics →

+ Follow this topic

Key players

Hugging Face Inkling NVIDIA Kimi K3 Moonshot AI OpenAI

Monday, 3 August 2026

Alibaba Qwen Releases Qwen3.8-Max: A 2.4 Trillion Parameter MoE Model and the Most Capable One in the Qwen Family to Date

MarkTechPost 3 weeks ago 48 ● 10 sources

Alibaba released Qwen3.8-Max, a 2.4-trillion-parameter mixture-of-experts model accepting text, image, and video input, with open weights coming next week. The hosted API costs $2 per million input tokens and $6 per million output tokens, with a 1-million-token context window and support for cached inputs at $0.25 per million tokens. The smaller 27B checkpoint will be the practical option for on-premise deployment, while performance gains over the previous version are largest in multimodal and agentic tasks rather than reasoning benchmarks.

Read the full story
Multimodal Models Qwen Mixture-of-Experts

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.