Tencent open-sources Hy3: a 295B MoE (21B active parameters); surpasses open-source models in search, trails GLM-5.2 in coding
Tencent released Apache-licensed Hy3, a 295B MoE (21B active parameters) model beating larger rivals...
AI BriefingTencent has open-sourced Hy3 under the Apache 2.0 license. It uses a 295B-parameter MoE architecture (21B active parameters). It performs strongly in agentic search: BrowseComp 84.2 and DeepSearchQA 91.0, outperforming all open-source models and approaching Claude Opus 4.8 and GPT-5.5. It trails Zhipu’s GLM-5.2 (744B total/40B active) on coding tasks. It has clear deployment advantages: under FP8, it uses <300GB, half the 744GB required by GLM-5.2. Its hallucination rate fell from 12.5% to 5.4%. A free API is available for two weeks.
Reported by 9 additional sources
- Tencent Hunyuan releases 1-bit and 4-bit versions of Hy3Tencent Hunyuan · July 15
- Tencent Hunyuan releases 1bit and 4bit quantized versions of Hy3, enabling the flagship AI model to run locally on a single GPUIT Home · Artificial Intelligence · July 14
- Tencent Hunyuan releases 1-bit/4-bit quantized versions of the Hy3 model; runs on a single GPUTencent Hunyuan · July 14
- Tencent Hunyuan releases quantized versions of Hy3: the 1-bit version can be deployed on a single GPU, while the 4-bit version delivers near-full performanceWeChat Official Account: Tencent Hunyuan · July 14
- Tencent Hunyuan Hy3 tops the OpenRouter rankingsTencent Hunyuan · July 13
- Tencent releases open-source MoE model Hy3, claiming performance on par with models 5 times its sizeThe Decoder: AI News · July 7
- Tencent Hunyuan releases the 295B MoE model Hy3Tencent Hunyuan · July 6
- Tencent Yuanbao integrates the Hunyuan Hy3 model, supporting free file processingIT Home · Artificial Intelligence · July 6
- Tencent Hunyuan releases and open-sources the Hy3 model today, with performance comparable to flagship models 2–5 times its sizeIT Home · Artificial Intelligence · July 6
Source: Rohan Paul · x.com