Model Intelligence Sheet
mrutkows/granite-4.0-3b-vision-GGUF overview
mrutkows/granite-4.0-3b-vision-GGUF GGUF downloads for local AI inference with guIDE.
Runs locally from ~950.0 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 |
|---|---|---|---|---|
| granite-4.0-3b-vision-Q4_K_M.gguf | GGUF | Q4_K_M | 2.09 GB | Download |
| granite-4.0-3b-vision-Q5_K_M.gguf | GGUF | Q5_K_M | 2.43 GB | Download |
| granite-4.0-3b-vision-Q6_K.gguf | GGUF | Q6_K | 2.80 GB | Download |
| granite-4.0-3b-vision-Q8_0.gguf | GGUF | Q8_0 | 3.63 GB | Download |
| granite-4.0-3b-vision-bf16.gguf | GGUF | BF16 | 6.82 GB | Download |
| granite-4.0-3b-vision-lora-f16.gguf | GGUF | F16 | 950.0 MB | Download |
| mmproj-model-f16.gguf | GGUF | F16 | 1.08 GB | Download |
Model Details
Run mrutkows/granite-4.0-3b-vision-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models