---
title: Hy4-preview-SF-FP8
canonical_url: "https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-FP8"
md_url: "https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-FP8.md"
repository: siliconflow/Hy4-preview-SF-FP8
last_updated: 2026-10-27
model_type:
  - hy_v4
architectures:
  - HYV4ForCausalLM
parameters: 782.7B
tensor_type:
  - I8
  - F32
  - BF16
library_name:
  - safetensors
downloads: 1746
stars: 1
---

# Hy4-preview-SF-FP8

> Hy4-preview-SF-FP8 - siliconflow 在 ModelScope 开源的模型。SiliconFlow block-FP8 (E4M3 block-128) of Tencent Hy4-preview

- **Repository**: siliconflow/Hy4-preview-SF-FP8
- **Parameters**: 782.7B
- **Downloads**: 1746
- **Stars**: 1
- **Last updated**: 2026-10-27

Source: https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-FP8

---

# Hy4-preview-SF-FP8

SiliconFlow crossingbits **block-FP8** (E4M3, block 128, FP32 scales) of Tencent [Hy4-preview](https://www.modelscope.cn/models/Tencent-Hunyuan/Hy4-preview).

License: Apache-2.0 (inherited from upstream).

## Quant Diff

| | Official `Hy4-preview-FP8` | This checkpoint |
|---|---|---|
| Weight format | ModelOpt MXFP8 (UE8M0, group 32) | crossingbits block-FP8 E4M3, block 128, `fp8_scale_w` FP32 |
| Activations | MXFP8 dynamic | per-token FP8 (runtime `fp8_scale_x`) |
| BF16 keep | `lm_head`, `embed_tokens`, `mlp.gate`, `linear_gate`, `indexer.weights_proj`, `eh_proj`, iHC `hc_fn` | same + MLA absorb `kv_b`/`k_b`/`v_b` |
| Experts | packed 3-D `gate_up_proj`/`down_proj` | unfused per-expert `gate_proj`/`up_proj`/`down_proj` |
| MTP | 1 layer, no iHC | quantized with main (`use_mtp: true`); `eh_proj` BF16 |

Calibration: C4, no rotate/smooth/clip.

Reported during PTQ: mean snr_err `4.61e-4`, KLD `9.73e-2`, rejection `0.361`, dead `0.0%`.

## Files

HuggingFace-style shards: `model-common-*.safetensors` + `model-experts-*.safetensors`, `quantize_config.json`.