First GGUF quants of Tencent's Hy3 (299B MoE), built before official llama.cpp support exists.
Hy3 dropped ~30 hours ago with only MLX and MXFP4 quants, both datacenter-sized. So I converted it myself using a community llama.cpp fork that implements the hy_v3 architecture.
What's in the repo:
- IQ1_M (62GB, fits a 128GB MacBook), IQ2_M (90GB), Q2_K (101GB), all with 1M context baked in via YaRN - IQ quants are importance-matrix: bootstrap style. The static Q2_K ran RAM-resident to compute the imatrix, then IQ1_M and IQ2_M were requantized from the archived f16 with it - Fixed chat template (the stock one uses .format() calls llama.cpp's Jinja rejects) - Build instructions for the fork, including the two gotchas that cost me three build attempts
Honesty section, because that is how these repos work: this is EXPERIMENTAL. Not needle-certified yet (1M is baked but unverified, certification ladder will be published either way). MTP layer exists in the checkpoint but no llama.cpp build can run hy_v3 MTP inference yet, so it is not included. Real gate outputs are on the card, misses and all, judge for yourself.
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop. Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
✅ 295B total / 21B active / 256K context ✅ Fused fast-and-slow thinking in a single model ✅ First model trained on Hunyuan's rebuilt pretraining + RL infra (Feb → Apr)
Benchmarks: 👉 SWE-Bench Verified, Terminal-Bench 2.0, BrowseComp, WideSearch — competitive results, particularly strong on agentic tool use 👉 Top score on Tsinghua's 2026 Spring math PhD qualifying exam 👉 Strong context-learning and instruction-following on Tencent's CL-bench / CL-bench-Life
Recently, I have open-sourced an AI emotional companion product based on openclaw, called opensoul.
On this platform, you can create a "soulmate" that matches your personality, and configure it with the skills, tools you want it to have, as well as the platforms it can integrate with (such as Telegram, Discord, etc.). You can even create group chats, invite multiple agents and your friends to chat about recent events, discuss projects together, and so on.
On the one hand, I hope it can better accompany you in daily life by virtue of its unique memory mechanism, self-feedback and iteration mechanism, and the modeling of users' emotions. On the other hand, I also hope it can help you better handle your work with its unique skills, tools and ability to deal with complex task scenarios.
Although the entire product has taken shape, I think there are still many areas that need adjustment and optimization. I also hope to rely on the strength of the community to do a good job in AI emotional companionship.
One year after the “DeepSeek Moment,” open source has become the default. Models, research, infrastructure, and deployment are increasingly shared to support large-scale, system-level integration.
This final blog examines how leading Chinese AI organizations are evolving ,and what this implies for the future of open source.
I submitted a "FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning" Paper by Tanyu Chen, Tairan Chen, Kai shen , Zhenghua Bao, Zhihui Zhang, Man Yuan, Yi Shi From
Chroma 1.0 enables real time spoken dialogue with personalized voice cloning through discrete speech representations and interleaved text audio token scheduling.
Chroma 1.0 , the world’s first open source, real time speech to speech model with voice cloning.
✨ Sparse MoE：196B/11B active ✨ Supports up to 256K context ✨ Multi-token prediction for fast decoding (100–300 tok/s) ✨ Runs locally on consumer hardware
They just dropped their first VLA and depth perception foundation model on huggingface. ✨ LingBot-VLA : - Trained on 20k hours of real-world robot data - 9 robot embodiments - Clear no-saturation scaling laws - Apache 2.0
