---
title: gemma-4-26B-A4B-GGUF
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/gemma-4-26B-A4B-GGUF"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/gemma-4-26B-A4B-GGUF.md"
repository: AI-ModelScope/gemma-4-26B-A4B-GGUF
last_updated: 2026-06-27
license: apache-2.0
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 46
stars: 0
---

# gemma-4-26B-A4B-GGUF

> gemma-4-26B-A4B-GGUF - AI-ModelScope 在 ModelScope 开源的模型。A few GGUF quants of the base model, as I could not find any. Made using llama.cpp at commit d0a6dfe, binaries at release b8683 Re-quantized with bf16 and re-uploaded. Original model:…

AI-ModelScope/gemma-4-26B-A4B-GGUF 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/gemma-4-26B-A4B-GGUF
- **License**: apache-2.0
- **Downloads**: 46
- **Stars**: 0
- **Last updated**: 2026-06-27

Source: https://www.modelscope.cn/models/AI-ModelScope/gemma-4-26B-A4B-GGUF

---

A few GGUF quants of the base model, as I could not find any. Made using llama.cpp at commit d0a6dfe, binaries at release b8683
Re-quantized with bf16 and re-uploaded.
Original model: https://huggingface.co/google/gemma-4-26B-A4B