- Services
Hunyuan is Tencent’s multi-modal model family spanning language, image, and video. Several Hunyuan checkpoints are open weight under permissive licenses.
See all models from TencentModels in family
8
Open weight
3
API only
5
Avg score
55.2
Top benchmark
90.4
GPQA
Total HF downloads
1.1M
Primary modality
Text
Context window
256K – 262K
First release
Jan 2025
Latest release
Oct 2026
Every release in the Hunyuan family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB64.7 | 295B | Oct 2026 | |
| 2 | Hunyuan Vision 1.5 ThinkingAPI | text | BB61.2 | — | Nov 2025 |
| 3 | Hunyuan TurboS (2025-04-16)API | text | BB60.4 | — | Apr 2025 |
| 4 | Hunyuan T1API | text | BB59.5 | — | Jul 2025 |
| 5 | Hunyuan TurboS (2025-02-26)API | text | BB57.1 | — | Feb 2025 |
| 6 | Hunyuan Turbo (0110)API | text | BB56.6 | — | Jan 2025 |
| 7 | image | CC46.9 | 80B | Sep 2025 | |
| 8 | image | DD35.1 | 80B | — |
When a family spans multiple modalities, the strongest model in each one.
How the family splits across text, image, video, audio, embedding, and decision releases.
When each release shipped, newest first. Useful for tracking version cadence.
Oct 23
Nov 30
Sep 28
Jul 10
Apr 15
Feb 25
Jan 9
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | text | BB64.7 | 295B | Oct 2026 | |
| 2 | image | CC46.9 | 80B | Sep 2025 | |
| 3 | image | DD35.1 | 80B | — |
Closed-source releases accessed through Tencent’s API.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | Hunyuan Vision 1.5 ThinkingAPI | text | BB61.2 | — | Nov 2025 |
| 2 | Hunyuan TurboS (2025-04-16)API |
The Hunyuan family is a series of AI models from Tencent. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, Hunyuan Hy3 is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Advertising disclosure: we earn commissions when you shop through the links below.
Vast.ai
Decentralized GPU marketplace with the lowest hourly prices.
RunPod
Pay-per-second GPU rentals starting at $0.20/hr.
Digital Ocean
Spin up a GPU droplet in minutes, starting at $0.75/hr.
Vultr
GPU cloud with hourly and monthly plans, starting at $0.50/hr.
GPU Mart
Dedicated GPU servers and VPS billed monthly, starting at $0.50/hr.
PPQ.ai
Multi-model inference gateway for production workloads.
Find Local Hardware
See which GPU, Mac, or workstation can run Hunyuan on-prem.
Local LLM Mini PCs
Compact machines that run Hunyuan on your desk. Chosen for local inference.
Benchmark data sourced from: Hugging Face, Arena.ai, Artificial Analysis.
BB60.4 |
| — |
| Apr 2025 |
| 3 | Hunyuan T1API | text | BB59.5 | — | Jul 2025 |
| 4 | Hunyuan TurboS (2025-02-26)API | text | BB57.1 | — | Feb 2025 |
| 5 | Hunyuan Turbo (0110)API | text | BB56.6 | — | Jan 2025 |
