tencent/Hy4-flash
image-text-to-text model by tencent
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](#license) [](https://huggingface.co/tencent/Hy4-flash) [](https://modelscope.cn/models/Tencent-Hunyuan/Hy4-flash) [](https://ai.gitcode.com/tencenthunyuan/Hy4-flash) Official Website | GitHub | GGUF Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens. Its 42-layer language backbone consists of one dense feed-forward layer and 41 MoE layers, with identity Hyper-Connections (iHC) supporting inter-layer information flow. A vision encoder (adapted from SigLIP2-So400m-Patch16-Res512) is connected to the backbone through an MLP projector. In addition to the backbone, a built-in 5-layer drafter, DFly2 (0.85B parameters), reuses the target model's KV cache and sparse indices to support long-context speculative decoding at a low, constant cost. Compared with Hy4, Hy4 Flash introduces three notable architectural changes: Bits-per-byte (BPB) on internal code & agent validation, lower is better: Few-shot pretrain benchmark evaluation: † Macro-averaged…
Read the full model card ↗ · Preview checked 2026-11-18T10:01:57.611Z
Inside the original model card — Document outline
- Table of Contents
- Model Introduction
- Pretrained model capability
- Practicality and Cost Efficiency
- Optimization Approach
- Task Performance and Cost
- User Blind Evaluation
- Appendix: Benchmark results
- News
- Model Links
- Quickstart
- Transformers
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
tencent/Hy4-flash is a image-text-to-text model repository published by tencent on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 68
- Hugging Face trending score
- 68
- Reported safetensors parameters
- 220,251,201,958
- Architecture
- HYV4FlashForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-17T03:44:46.000Z
- Last modified
- 2026-11-18T04:24:08.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-18T06:59:26.317Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.