Model Intelligence Sheet
ggml-org/gemma-4-31B-it-GGUF overview
gemma 4 31B it Run with https://llama.app bash llama serve hf ggml org/gemma 4 31B it GGUF Source models https://huggingface.co/google/gemma 4 31B it https://h…
Runs locally from ~267.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
10 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| dflash-gemma-4-31B-it-BF16.gguf | GGUF | BF16 | 2.88 GB | Download |
| dflash-gemma-4-31B-it-Q8_0.gguf | GGUF | Q8_0 | 1.53 GB | Download |
| gemma-4-31B-it-BF16.gguf | GGUF | BF16 | 57.20 GB | Download |
| gemma-4-31B-it-Q4_0.gguf | GGUF | Q4_0 | 16.76 GB | Download |
| gemma-4-31B-it-Q8_0.gguf | GGUF | Q8_0 | 30.39 GB | Download |
| mmproj-gemma-4-31B-it-BF16.gguf | GGUF | BF16 | 1.12 GB | Download |
| mmproj-gemma-4-31B-it-Q8_0.gguf | GGUF | Q8_0 | 772.0 MB | Download |
| mtp-gemma-4-31B-it-BF16.gguf | GGUF | BF16 | 910.6 MB | Download |
| mtp-gemma-4-31B-it-Q4_0.gguf | GGUF | Q4_0 | 267.0 MB | Download |
| mtp-gemma-4-31B-it-Q8_0.gguf | GGUF | Q8_0 | 490.8 MB | Download |
Model Details
| Model ID | ggml-org/gemma-4-31B-it-GGUF |
|---|---|
| Author | ggml-org |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | google/gemma-4-31B-it |
| Last modified | 2026-07-26T02:47:36.000Z |
Model README
---
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- gguf
- quantized
base_model:
- google/gemma-4-31B-it
---
gemma-4-31B-it
Run with https://llama.app
llama serve -hf ggml-org/gemma-4-31B-it-GGUFSource models
- https://huggingface.co/google/gemma-4-31B-it
- https://huggingface.co/google/gemma-4-31B-it-assistant
- https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized
- https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
- https://huggingface.co/z-lab/gemma-4-31B-it-DFlash
TODOs
- add info
> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert
Run ggml-org/gemma-4-31B-it-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models