Model Intelligence Sheet
ToastyPigeon/Gemma-4-Test-GGUFs overview
A repo of test models for when I typed wrong trying to upload to Gemma4 Test GGUFs https://huggingface.co/ToastyPigeon/Gemma4 Test GGUFs
Runs locally from ~11.80 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
15 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Gemma-4-12B-AB-itbase-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| Gemma-4-12B-Full-CPT-ItVec-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| Gemma-4-12B-Full-CPT-ItVec-a08-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| Gemma-4-12B-Full-CPT-ItVec-a09-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| Gemma-4-Delerp-Rp-12B-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| OrionKitchoon-26B-A4B-IQ4_XS.gguf | GGUF | IQ4_XS | 13.33 GB | Download |
| OrionKitchoon-26B-A4B-Q4_K_S.gguf | GGUF | Q4_K_S | 14.40 GB | Download |
| g4-31b-g3native-ep1.Q4_K_S.gguf | GGUF | GGUF | 16.54 GB | Download |
| g4-31b-g3native-ep2.Q4_K_S.gguf | GGUF | GGUF | 16.54 GB | Download |
| gemma-4-12b-alpaca-cpt-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| gemma-4-12b-cpt-sft-rp-chapters-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| gemma-4-12b-it-sft-rp-chapters-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| gemma-4-12b-it-sys-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| gemma-4-12b-itvec-mix-Q8_0.gguf | GGUF | Q8_0 | 11.80 GB | Download |
| gemma-4-31b-glitterlike-Q4_K_S.gguf | GGUF | Q4_K_S | 16.54 GB | Download |
Model Details
| Model ID | ToastyPigeon/Gemma-4-Test-GGUFs |
|---|---|
| Author | ToastyPigeon |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-10-18T00:16:22.000Z |
Model README
A repo of test models for when I typed wrong trying to upload to Gemma4-Test-GGUFs
Run ToastyPigeon/Gemma-4-Test-GGUFs with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models