TLDRocket
Sign in

Multimodal AI

91 summarised stories about Multimodal AI, each linking back to the original source. Browse all topics →

+ Follow this topic

Friday, 18 September 2026

PrismML launches Bonsai 2 27B, a high-intelligence AI model so small it fits on consumer hardware

SiliconANGLE 4 weeks ago 48 ● 4 sources

PrismML launched Bonsai 2 27B, a second-generation ultra-compact multimodal AI model designed to run on PCs and some high-end mobile devices. It reduces a Qwen3.8 27B model from about 56 GB in 16-bit uncompressed form to about 5.9 GB while retaining about 98.2% of capabilities. Model users can now run this AI locally with lower memory, compute, and power needs, with weights released under Apache 2.0.

Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use

MarkTechPost 4 weeks ago 11 ● 3 sources

Alibaba’s Qwen released Qwen3.8-Omni-Flash, an omni-modal model that takes text, images, audio, and video and outputs text with agentic audio-video understanding, reasoning, and tool use. The model supports a 1M-token context window. It is available only via hosted APIs (no open weights), alongside Qwen-MM-Plugins released under Apache-2.0 to help agent harness multimodal capabilities.

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.