Skip to content
NEWSee what changed →

tencent · hy_v3

Hy3

Hy3 by tencent: a 298.8B-parameter mixture-of-experts open-weight model under the apache-2.0 license.

apache-2.0Mixture of experts262K contextAuto-imported · not yet reviewed

981,065 downloads · 995 likes · Model card · synced 2026-11-19

Specifications

Parameters
298.8B (12.5B active)
Architecture
moe · hy_v3
Layers
80
Hidden size
4,096
KV heads · head dim
8 · 128
Vocabulary
120,832
Native dtype
—
Context window
262,144 tokens
Released
2026-07-02
Last modified on Hub
2026-07-20

Features & licensing

License
apache-2.0
Commercial use
Yes
Modalities
text
Tool / function calling
No
Reasoning mode
No
Languages
EN
Quantised variants on Hub
FP8, GGUF, bitsandbytes
Pipeline
text-generation
transformerssafetensorshy_v3text-generationhunyuanhy3moeconversationaleval-resultsendpoints_compatible

Task fit

Editorial scores (0–100) used by the recommendation engine.

  • Chat70
  • RAG / Q&A70
  • Code70
  • Summarisation70
  • Extraction70
  • Agents70

Hardware to run Hy3

Weights need about 657 GB at FP16, 345 GB at INT8 and 197 GB at INT4. The KV cache adds roughly 328 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 341.4 GB, which fits on 5 × NVIDIA A100 (80 GB).

GPU configurations at the reference workload
ConfigurationVRAMUtilisationEst. first tokenCloud / month
8 × NVIDIA L40S (48 GB)384 GB89 %~0.2 s$11,096
5 × NVIDIA A100 (80 GB)recommended400 GB85 %~0.1 s$11,680
5 × NVIDIA H100 (80 GB)400 GB85 %~0.0 s$16,425

Estimates only. Run an assessment for your own traffic.

Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.