Model Intelligence Sheet
magnitudedev/gemma-4-31B-it-qat-MTP-GGUF overview
gemma 4 31B it qat MTP GGUF Q4 0 GGUF of google/gemma 4 31B it qat q4 0 unquantized assistant https://huggingface.co/google/gemma 4 31B it qat q4 0 unquantized…
Runs locally from ~267.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma-4-31B-it-qat-MTP-Q4_0.gguf | GGUF | Q4_0 | 267.0 MB | Download |
Model Details
| Model ID | magnitudedev/gemma-4-31B-it-qat-MTP-GGUF |
|---|---|
| Author | magnitudedev |
| Pipeline | — |
| License | apache-2.0 |
| Base model | google/gemma-4-31B-it-qat-q4_0-unquantized-assistant |
| Last modified | 2026-10-11T07:44:46.000Z |
Model README
---
license: apache-2.0
base_model: google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
tags:
- gguf
- mtp
- speculative-decoding
- magnitude
inference: false
---
gemma-4-31B-it-qat-MTP-GGUF
Q4_0 GGUF of google/gemma-4-31B-it-qat-q4_0-unquantized-assistant for use with Magnitude.
This is the MTP draft model for speculative decoding with the Gemma 4 31B QAT model.
Artifact
- File:
gemma-4-31B-it-qat-MTP-Q4_0.gguf - SHA-256:
3a5e99fd8d0b23afb1fccd1ee0c9ebd1f571d00399c2dae2292d217feeec0f6b - Source revision:
96d4c8ca3cb38c107a8478587878124895d1e844 - GGUF from unsloth/gemma-4-31B-it-qat-GGUF (
mtp-gemma-4-31B-it.gguf)
Run magnitudedev/gemma-4-31B-it-qat-MTP-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models