Tencent's Sherry quantization shrinks Hy4 model size by 7x
QuixiAI · x · 2026-09-01
Tencent's Sherry quantization method compresses model weights to 1.25 bits. Applied to Hy4 Preview, it reduces size from 1.5TB to 214GB with minimal accuracy loss (e.g., MCP Atlas 83.7→83.2). It also enables stitching GPUs across machines.
Related event: Tencent Hunyuan's AngelSlim Shrinks Hy4-preview from 1.5TB to 214GB(5 posts)→
More from Research
- Encoding Turing machine tapes in Peano Arithmetic via Gödel's beta function — jessi_cata · 2026-10-18
- SimInfinity: open-source robotic simulation benchmark with 10K real-world tasks — joemeno · 2026-10-18
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Meta paper introduces "agent plasticity": best-performing agent isn't the most efficient learner — rohanpaul_ai · 2026-10-18
- SAE weight editing steers robot behavior at inference time, IIIT Hyderabad paper lands IJCAI Safe Physical AI workshop — ponguru · 2026-10-18
- NTU-led survey reviews nearly 200 papers on affordance learning for embodied AI — jiqizhixin · 2026-10-18