---
title: Hy4-preview-SF-WFP4AFP8
canonical_url: "https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-WFP4AFP8"
md_url: "https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-WFP4AFP8.md"
repository: siliconflow/Hy4-preview-SF-WFP4AFP8
last_updated: 2026-10-15
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - hy_v4
architectures:
  - HYV4ForCausalLM
parameters: 428.5B
tensor_type:
  - U8
  - BF16
  - I8
  - F32
library_name:
  - safetensors
language:
  - en
  - zh
downloads: 2414
stars: 1
---

# Hy4-preview-SF-WFP4AFP8

> Hy4-preview-SF-WFP4AFP8 - siliconflow 在 ModelScope 开源的模型。Hy4-preview-SF-WFP4AFP8

siliconflow/Hy4-preview-SF-WFP4AFP8 是 ModelScope 魔搭社区上的 428.5B 参数text-generation模型，采用 apache-2.0 许可。

- **Repository**: siliconflow/Hy4-preview-SF-WFP4AFP8
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 428.5B
- **Downloads**: 2414
- **Stars**: 1
- **Last updated**: 2026-10-15

Source: https://www.modelscope.cn/models/siliconflow/Hy4-preview-SF-WFP4AFP8

---

# Hy4-preview-SF-WFP4AFP8

## Quant Diff

CrossingBits PTQ of Tencent Hunyuan `Hy4-preview` (`hy_v4`), from the official MXFP8 release
`Tencent-Hunyuan/Hy4-preview-FP8` (dequantized layer by layer, then quantized).
Same layout as `siliconflow/DeepSeek-V4.1-Flash-SF-WFP4AFP8`: only routed experts are FP4.

Changed from the previous build (tag `20260910`, Hopper layout): every non-expert FP8 linear moved from
block-128 FP8 with FP32 scales to MXFP8 (group 32, UE8M0 scales), and `self_attn.linear_gate` went from FP8 back to BF16.
Calibration KLD dropped from 0.281 to 0.078. FP4 routed experts are unchanged in format (FP4 E2M1 g32 + FP8 E4M3 g32 activations).
This build targets Blackwell serving; the shard layout changed (`model-common-*-of-00009`).

| | |
|---|---|
| Recipe | `weight_fp4_activation_fp8`, group 32, `ue8m0` / `e4m3` |
| Routed experts (`mlp.experts.*`) | FP4 E2M1 weights + FP8 E4M3 activations (g32) |
| MLA `q_a` / `kv_a` / `q_b` / `o`, indexer `wk` / `wq_b`, dense layer-0 FFN, `mlp.shared_experts.{gate,up,down}_proj` | MXFP8 W8A8 g32 |
| BF16 | router (`mlp.gate`), MLA absorb (`kv_b` / `k_b` / `v_b`), `indexer.weights_proj`, `self_attn.linear_gate`, MTP `eh_proj`, embed, `lm_head` |
| MTP | enabled (`mtp_layers.0`); shares the target `embed_tokens` / `lm_head` as in the provider checkpoint |

Full quantization metadata is in `quantize_config.json`.

## Validation

| Check | Result |
|---|---|
| Calibration KLD (`quantize_config.json`) | 0.078 (previous build 0.281) |
| Weight dequant vs source | MXFP8 layers identical to the MXFP8 source (cos 1.0000); FP4 experts cos ≥ 0.991 |
| Unquantized tensors | identical to source (BF16/FP32) |
| Long-form text decode (chat template, default reasoning) | coherent; exits think and answers (plans ~500 tokens before answering) |
| MTP top-1 / top-5 acceptance (crossingbits eval) | 0.602 / 0.746 |

Not yet validated:

- **Serving engine.** FP4 GEMMs need Blackwell; this checkpoint was validated only with crossingbits reference
  inference, not yet served on an engine.

The upstream model card (Chinese) is kept as `README_CN.md`; see `LICENSE` for the Apache-2.0 license.