Model Intelligence Sheet
noctrex/Shieldstral-1.0-3B-GGUF overview
These are quantizations of the model mistralai / Shieldstral 1.0 3B https://huggingface.co/mistralai/Shieldstral 1.0 3B . imatrix has been calculated with text…
Runs locally from ~2.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
12 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Shieldstral-1.0-3B-BF16.gguf | GGUF | BF16 | 6.39 GB | Download |
| Shieldstral-1.0-3B-F16.gguf | GGUF | F16 | 6.39 GB | Download |
| Shieldstral-1.0-3B-IQ4_NL.gguf | GGUF | IQ4_NL | 1.91 GB | Download |
| Shieldstral-1.0-3B-IQ4_XS.gguf | GGUF | IQ4_XS | 1.82 GB | Download |
| Shieldstral-1.0-3B-Q4_K_M.gguf | GGUF | Q4_K_M | 2.00 GB | Download |
| Shieldstral-1.0-3B-Q5_K_M.gguf | GGUF | Q5_K_M | 2.30 GB | Download |
| Shieldstral-1.0-3B-Q6_K.gguf | GGUF | Q6_K | 2.63 GB | Download |
| Shieldstral-1.0-3B-Q8_0.gguf | GGUF | Q8_0 | 3.40 GB | Download |
| imatrix.gguf | GGUF | GGUF | 2.9 MB | Download |
| mmproj-BF16.gguf | GGUF | BF16 | 810.5 MB | Download |
| mmproj-F16.gguf | GGUF | F16 | 801.4 MB | Download |
| mmproj-F32.gguf | GGUF | F32 | 1.56 GB | Download |
Model Details
| Model ID | noctrex/Shieldstral-1.0-3B-GGUF |
|---|---|
| Author | noctrex |
| Pipeline | image-text-to-text |
| License | — |
| Base model | mistralai/Shieldstral-1.0-3B |
| Last modified | 2026-08-05T12:25:14.000Z |
Model README
---
pipeline_tag: image-text-to-text
base_model:
- mistralai/Shieldstral-1.0-3B
---
These are quantizations of the model mistralai / Shieldstral-1.0-3B.
imatrix has been calculated with text\_eur\_large
Updated mmproj that where failing to load.
Run noctrex/Shieldstral-1.0-3B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models