Note on Thinking/Reasoning Display: The model thinks correctly (generates [THINK]...[/THINK] tags internally), but LM Studio 0.4.17 does not display thinking in a collapsible reasoning section. LM Studio only natively supports DeepSeek-style tags for reasoning display. The model works perfectly via llama-server with --reasoning on flag. This is a known limitation of LM Studio for the Ministral reasoning format.

MXFP4 quantization of mistralai/Ministral-3-14B-Reasoning-2512, a 14B parameter reasoning and vision model from Mistral AI.

About the Model

Ministral 3 14B Reasoning is a dense transformer with 40 layers, 5120 hidden dimension, and 24-layer Pixtral ViT vision encoder. It supports:

Advanced reasoning with chain-of-thought capabilities
Code generation and debugging across multiple languages
Vision understanding via multimodal image input
Tool calling with native function calling support
262K context window with YaRN scaling

Quantization

This GGUF was quantized from Mistral's official BF16 GGUF using llama.cpp (build 537). The BF16 weights were dequantized to F32 during quantization, then quantized to MXFP4 format.

MXFP4 (Microscaling FP4) uses block-wise quantization with shared exponents per block, providing better precision than standard FP4 for the same memory footprint.

Files

File	Size	Description
`ministral-3-14b-reasoning-2512-mxfp4.gguf`	~6.9 GB	MXFP4 quantized model weights
`mmproj-ministral-3-14b-reasoning-2512-f16.gguf`	~820 MB	Vision projector (F16, unquantized)

Usage

llama.cpp

bash

# Server mode with OpenAI-compatible API
llama-server \
  -m ministral-3-14b-reasoning-2512-mxfp4.gguf \
  --mmproj mmproj-ministral-3-14b-reasoning-2512-f16.gguf \
  -ngl 99 \
  --host 0.0.0.0 \
  --port 8080

# Direct inference
llama-cli \
  -m ministral-3-14b-reasoning-2512-mxfp4.gguf \
  --mmproj mmproj-ministral-3-14b-reasoning-2512-f16.gguf \
  -ngl 99 \
  -p "Explain the chain of thought for solving: what is 15 * 23?"

LM Studio

Download both files from this repository
Load the main GGUF file in LM Studio
Load the mmproj file for vision support
Set GPU offload layers to maximum

Architecture

Parameters: 14B (dense transformer)
Layers: 40
Hidden dimension: 5120
Attention heads: 32 (8 KV heads for GQA)
Vision encoder: 24-layer Pixtral ViT
Context: 262K (YaRN scaled from 16K base)
Vocabulary: Mistral Tekken tokenizer (131K tokens)

Hardware Requirements

Minimum: 8 GB VRAM for text-only, 10 GB for vision
Recommended: 16 GB VRAM for full GPU offload
Disk: ~7.9 GB for model + mmproj

Quantization Details

Metric	Value
Source format	BF16 GGUF (Mistral official)
Output format	MXFP4
Approximate BPW	~4.37
Quantized with	llama.cpp build 537

License

Apache 2.0 — same as the base model.

FreedomAISVR/Ministral-3-14B-Reasoning-2512-MXFP4-GGUF

Ministral 3 14B Reasoning-2512 — MXFP4 GGUF