Running the MiniMax audio and video large model on a single graphics card reduced the time from 6 minutes to 56 seconds!
💥 NVIDIA Research has just open sourced Sol-H3: on a single DGX Spark, it can fully end-to-end generate 768p (1344×768), 5-second, high-definition video with native synchronized audio, taking only 56.17 seconds, a full 6.7 times faster! Video memory trick: [Resident video memory 116.9G]: DGX Spark video memory upper limit…
[Special Feature/Gemini 3.8 TTS] Will the voice created by AI disappear in a year?
We compared the voice AI of four companies using the same script on the AI news radio broadcast every morning. Miho's voice explained in the video was also created using Gemini 3.8 TTS. ■ Results (approximately 800 characters per topic, one measurement each) ・Gemini 3.8…
It's been quiet here for a bit.
Behind the scenes though, we've been busy shipping and building. This week: daily updates, one for each day, catching you up on everything. Kicking off with OpenClaw 2.0, now live on OctaSpace, bundled with Qwen 3.8. no API keys required. More
Every single rtx 5060 ti 16gb vram owner
Bonsai2 27b dense flies on your gpu with the full 262k context window, the mtp head and vision all loaded at once, and it runs at 67 tok/s. 262k context + mtp head + vision on one card: 15.2 of 15.9 gb 67 tok/s with the mtp head, 71
You have reached the end of the archive
All of qwen38