gcoli/Ministral-3-3B-Base-2512-Q4_K_M-GGUF overview
Ministral 3 3B Base 2512 Q4 K M GGUF Text only Q4 K M GGUF quantization of mistralai/Ministral 3 3B Base 2512 https://huggingface.co/mistralai/Ministral 3 3B B…
Runs locally from ~2.00 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Ministral-3-3B-Base-2512-Q4_K_M.gguf | GGUF | Q4_K_M | 2.00 GB | Download |
Model Details
| Model ID | gcoli/Ministral-3-3B-Base-2512-Q4_K_M-GGUF |
|---|---|
| Author | gcoli |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | mistralai/Ministral-3-3B-Base-2512 |
| Last modified | 2026-08-14T12:55:12.000Z |
Model README
---
base_model: mistralai/Ministral-3-3B-Base-2512
license: apache-2.0
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- mistral
- q4_k_m
- base
- text-generation
---
Ministral 3 3B Base 2512 Q4 K M GGUF
Text-only Q4_K_M GGUF quantization of mistralai/Ministral-3-3B-Base-2512. No vision projector is included.
File
| File | Format | Size | SHA-256 |
| --- | --- | ---: | --- |
| Ministral-3-3B-Base-2512-Q4_K_M.gguf | GGUF V3 Q4_K_M | 2,147,024,224 bytes | 9a565ad0c80c9a726db01c74e35ebb6ce83adfa2ec7bdb1e074aec55039d5f18 |
Conversion
The original BF16 weights were first converted to F16 GGUF with the official llama.cpp converter at tag b9402 using convert_hf_to_gguf.py --outtype f16 --mistral-format. That F16 GGUF was then quantized with the official llama-quantize build 10360 using Q4_K_M. No importance matrix was used.
The file was successfully loaded with KeyType's vendored llama.cpp b9402 runtime. Its autocomplete profile self-check passed 6 of 6 checks, and an actual decode smoke test passed.
Run gcoli/Ministral-3-3B-Base-2512-Q4_K_M-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models