Tencent's Hy4 Preview: 1.25-bit Quantization Cuts Model Size by 7x
ccerrato147 · x · 2026-09-01
Tencent's Hy4 model preview utilizes the Sherry quantization method, reducing weight precision to 1.25 bits. This shrinks the model size from 1.5TB to 214GB with negligible quality loss. It also enables stitching GPUs across multiple machines to work as one. Both GGUF quantized and original models are available.
Related event: Tencent Hunyuan's AngelSlim Shrinks Hy4-preview from 1.5TB to 214GB(5 posts)→
More from Infra
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- SGLang Summit sponsors jump from 11 to 36 in one week — ying11231 · 2026-10-18
- Oracle CDS hits record 300bps, called first AI trade domino after Barclays sell downgrade — arthurcolle · 2026-10-18
- Agent Coding Workflow Would Cost ~$40k/Month on API Pricing, Dev Reveals — ChrisRackauckas · 2026-10-18
- PS5LM: llama.cpp port turns a jailbroken PS5 into a home LLM server (500+ GitHub stars) — wateriscoding · 2026-10-18