Model Intelligence Sheet
Anbeeld/gemma-4-31B-it-DFlash-GGUF overview
Gemma 4 31B IT DFlash GGUF llama.cpp quantizations of z lab DFlash draft model https://huggingface.co/z lab/gemma 4 31B it DFlash for Gemma 4 31B IT https://hu…
Runs locally from ~551.4 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
7 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma4-31b-it-dflash-Q2_K.gguf | GGUF | Q2_K | 551.4 MB | Download |
| gemma4-31b-it-dflash-Q3_K_M.gguf | GGUF | Q3_K_M | 714.0 MB | Download |
| gemma4-31b-it-dflash-Q4_K_M.gguf | GGUF | Q4_K_M | 870.4 MB | Download |
| gemma4-31b-it-dflash-Q5_K_M.gguf | GGUF | Q5_K_M | 1.01 GB | Download |
| gemma4-31b-it-dflash-Q6_K.gguf | GGUF | Q6_K | 1.19 GB | Download |
| gemma4-31b-it-dflash-Q8_0.gguf | GGUF | Q8_0 | 1.53 GB | Download |
| gemma4-31b-it-dflash-bf16.gguf | GGUF | BF16 | 2.88 GB | Download |
Model Details
| Model ID | Anbeeld/gemma-4-31B-it-DFlash-GGUF |
|---|---|
| Author | Anbeeld |
| Pipeline | text-generation |
| License | — |
| Base model | z-lab/gemma-4-31B-it-DFlash |
| Last modified | 2026-07-19T02:30:05.000Z |
Model README
---
base_model: z-lab/gemma-4-31B-it-DFlash
tags:
- transformers
- safetensors
- qwen3
- dflash
- speculative-decoding
- block-diffusion
- draft-model
- efficiency
- qwen
- gemma
- diffusion-language-model
- text-generation
- arxiv:2602.06036
- license:apache-2.0
- text-generation-inference
- endpoints_compatible
- region:us
---
Gemma 4 31B IT DFlash GGUF
llama.cpp quantizations of z-lab DFlash draft model for Gemma 4 31B IT.
Run Anbeeld/gemma-4-31B-it-DFlash-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models