Hunyuan Releases Low-Bit Version of Hy3
_akhaliq · x · 2026-07-15
Tencent Hunyuan has released 1-bit and 4-bit versions of Hy3.
- These are low-bit versions of a flagship 295B model, officially claimed to be capable of running on a single GPU.
- Supports running via llama.cpp with MTP enabled, aiming to deliver strong reasoning capabilities at lower hardware costs.
- Official benchmarks and download links are provided, encouraging developers to try building with it directly.
Related event: Tencent Hunyuan ships 1-bit/4-bit quantized Hy3 for single-GPU deployment(5 posts)→
More from Models
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27