Reviews/AI MODELS/Tencent Hy3-preview
T

Tencent Hy3-preview

Tencent's first open-source frontier MoE — 295B params, 21B active, free on HuggingFace

PriceOpen Source (free on HuggingFace, free tier on OpenRouter)Reviewed2026-04-23
Verdict — Ship
3 Ships1 Skips
Visit huggingface.co

The Panel's Take

Tencent's Hy3-preview is the company's first public frontier-class language model, released April 23 as open weights on Hugging Face. The model is a 295B parameter Mixture-of-Experts architecture with only 21B parameters active per token — keeping inference costs comparable to much smaller dense models while reaching capabilities that compete with leading proprietary systems. The release comes under new leadership: Yao Shunyu, a former OpenAI researcher, joined Tencent in early 2026 to build out its frontier AI effort. The team claims to have gone from project start to public release in under three months — an unusually fast timeline for a model of this scale. The 256K context window and strong performance on agentic and coding benchmarks position it directly against GLM-5.1 and Qwen3.6 in the open-source frontier race. Free inference is available on OpenRouter's free tier at launch, with the model also appearing on Hugging Face's Inference API. The architecture uses 192 routed experts in a hybrid dense-MoE configuration. For teams needing a capable open-weights model for agentic workflows without paying proprietary API rates, Hy3-preview arrives as a credible option at a remarkable cost-to-capability ratio.

Share this verdict

Tencent Hy3-preview verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026

Weekly AI Tool Verdicts

Get the next verdict in your inbox

7 critics review a new AI tool every day. Weekly digest — free.

Embed this verdict

Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.

Ship · 7.5/10
HTML badge
<a href="https://shiporskip.io/api/badge-click/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026" alt="Tencent Hy3-preview Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![Tencent Hy3-preview Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026)](https://shiporskip.io/api/badge-click/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026)
Iframe widget
<iframe src="https://shiporskip.io/embed/tencent-hy3-preview-295b-moe-open-source-frontier-21b-active-2026" title="Tencent Hy3-preview ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

295B MoE with 21B active per token is a sweet spot for production use — you get frontier-quality outputs at a fraction of the compute cost. The 256K context and agent-optimized design make this immediately useful for complex workflow automation. Worth running evals against your specific use case.

Helpful?

Tencent hasn't published a full technical report yet, so benchmark claims are hard to independently verify. The 'three months to frontier' narrative sounds impressive but raises questions about training data sourcing and evaluation rigor. Preview releases from large Chinese labs have historically required patience before production stability.

Helpful?

The pace of open-source frontier models from Chinese labs is accelerating faster than anyone predicted — we now have credible open-weight competition from Alibaba, Zhipu, Xiaomi, and Tencent simultaneously. This is geopolitically significant and means the open-source ecosystem will stay competitive with proprietary models for years.

Helpful?

For multilingual creative work — especially for Chinese market content — having a frontier-quality open-source model from a Chinese lab is meaningful. The free OpenRouter tier means creators can experiment without API budgets.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later