---
title: granite-4.0-h-small-FP8
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/granite-4.0-h-small-FP8"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/granite-4.0-h-small-FP8.md"
repository: AI-ModelScope/granite-4.0-h-small-FP8
last_updated: 2025-10-09
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - granitemoehybrid
architectures:
  - GraniteMoeHybridForCausalLM
base_model:
  - ibm-granite/granite-4.0-h-small
base_model_relation: quantized
parameters: 32.6B
tensor_type:
  - F8_E4M3
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 81
stars: 0
tags:
  - language
  - granite-4.0
  - gguf
---

# granite-4.0-h-small-FP8

> granite-4.0-h-small-FP8 - AI-ModelScope 在 ModelScope 开源的模型。Granite 4.0 H-Small (FP8)

AI-ModelScope/granite-4.0-h-small-FP8 是 ModelScope 魔搭社区上的 32.6B 参数text-generation模型，采用 apache-2.0 许可，基于 ibm-granite/granite-4.0-h-small 构建，可用 deploy_task text/emb、vllm 0.9.2 部署。

- **Repository**: AI-ModelScope/granite-4.0-h-small-FP8
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 32.6B
- **Base model**: ibm-granite/granite-4.0-h-small
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Tags**: language, granite-4.0, gguf
- **Downloads**: 81
- **Stars**: 0
- **Last updated**: 2025-10-09

Source: https://www.modelscope.cn/models/AI-ModelScope/granite-4.0-h-small-FP8

---

### Granite 4.0 H-Small (FP8)

📣 **Update [10-07-2025]:** Added a *default system prompt* to the chat template to guide the model towards more *professional, accurate, and safe* responses.

> [!NOTE]
> This repository contains the FP8 version of **Granite-4.0-H-Small**.
>
> Please refer to the the original instruct model's model card for additional details:
> https://huggingface.co/ibm-granite/granite-4.0-h-small