Skip to content
ModelListedExternal
Download

Gemma 4 31B GGUF

> [!IMPORTANT] > This model is automatically converted using

Sourcehuggingface.co/ggml-org/gemma-4-31B-GGUF/tree/7056174770082d10607fc2e31ef39216b291c0bf
KindOtherBase modelgoogle/gemma-4-31BVersionRevision 7056174Bgrade

Model source

Kind
Other
File size
30.4–57.2 GB
Base model
google/gemma-4-31B
Version
vRevision 7056174
Updated
Oct 3, 2026
Downloads
5.1K
Source
Hugging Face

Source description

gemma-4-31B

Run with https://llama.app

llama serve -hf ggml-org/gemma-4-31B-GGUF

Source models

TODOs

  • add info

[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert

Sources

1 source
Hugging FacePrimaryVersion 7056174770082d10607fc2e31ef39216b291c0bf
huggingface.co/ggml-org/gemma-4-31B-GGUF/tree/7056174770082d10607fc2e31ef39216b291c0bf

Verified Aug 20

Model artifacts

2 artifacts

gemma-4-31B-BF16.gguf

gguf · 57.2 GB · SHA-256 cc5d470db4b8…bc61 · Hugging Face

Download

gemma-4-31B-Q8_0.gguf

gguf · 30.4 GB · SHA-256 2b739f4d97c7…400f · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeAug 20huggingface.co/ggml-org/gemma-4-31B-GGUF

--- license: apache-2.0 pipeline_tag: image-text-to-text tags: - gguf - quantized base_model: - google/gemma-4-31B --- # gemma-4-31B Run with https://llama.app ```bash llama serve -hf ggml-org/gemma-4-31B-GGUF ``` ### Source models - https://huggingface.co/google/gemma-4-31B ### TODOs - add info > [!IMPORTANT] > This model is automatically converted using https://github.com/ggml-org/convert

NoteAug 20huggingface.co/ggml-org/gemma-4-31B-GGUF

Source context: 5075 downloads · 1 likes · Pipeline image-text-to-text · Repo ggml-org/gemma-4-31B-GGUF