Tencent Hunyuan Releases Quantized Hy3
victormustar · x · 2026-07-14
Tencent Hunyuan has released 1-bit and 4-bit versions of Hy3.
- This is a flagship MoE model with 295B parameters. Officially claimed to be leading in its size class, it is competitive with much larger flagship models.
- Quantized versions can run via llama.cpp. With MTP enabled, it can be deployed on a single GPU, emphasizing strong intelligence capabilities at lower hardware costs.
- The release is under the Apache 2.0 open-source license, making it suitable for commercial use, and includes a 2-week free API.
Related event: Tencent Hunyuan ships 1-bit/4-bit quantized Hy3 for single-GPU deployment(5 posts)→
More from Infra
- Anthropic's S-1 Reveals Over $600B in Infrastructure Commitments Across Google, Amazon, Microsoft — cedric_chee · 2026-10-26
- Anthropic S-1 reveals 48 cents of compute cost per dollar of Q2 revenue — nmasc_ · 2026-10-26
- Persistent AI joins UR network to route private AI inference with encrypted, IP-hidden traffic — 0xSammy · 2026-10-26
- Anthropic's disclosed compute commitments: $114.5B Google, $161.2B Broadcom top the list — BenBajarin · 2026-10-26
- SpaceX strikes $40B deal with Apollo Global to lease AI chips and data center hardware — Polymarket · 2026-10-26
- SpaceX AI revenue up 830%, Claude designs 318K antivenom proteins in 64 hours — PeterDiamandis · 2026-10-26