Ministral-3 Guide: VRAM Requirements, GGUF Builds, Model Files

Everything Local Model Watch has published about the Ministral-3 family: 2 article(s) covering the base model and its fine-tunes, plus converted builds we tracked after publication. Memory requirements below are computed by this site from file sizes, not quoted from model cards. Part of our model family index.

At a Glance

Item Value
Base model(s) mistralai/Ministral-3-3B-Base-2512
Publisher Mistral AI
Parameters 4.4B
License (model card) apache-2.0
Smallest VRAM tier 4GB
Articles 2

Hardware Requirements

Estimated requirements (calculated by Local Model Watch) — 4.4B parameters

Your VRAM Quantization File size Est. memory needed
4GB (laptop iGPU / phone class) Q6_K 2.6GB 3.2GB
8GB (RTX 4060 / 3060 Ti, etc.) F16 6.4GB 7.7GB

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. File sizes are measured from the converted build mradermacher/Voxtral-Mini-4B-Realtime-Arabic-GGUF. Compare with other models in our VRAM quick reference. What the quantization names mean: glossary.

Figures are for mistralai/Voxtral-Mini-4B-Realtime-Arabic, the most recent model in this family with a hardware estimate.

Can You Run It Locally?

The publisher distributes this model as safetensors.

Compression: the Q6_K build measures 5.04 bits per weight — about 32% the size of the original 16-bit weights, calculated by this site from the actual file sizes.

Compiled by this site’s code from the published formats and the license field.

Distributed Files

Weight files published in mistralai/Voxtral-Mini-4B-Realtime-Arabic, listed by this site from the Hugging Face API. Sizes are the actual file sizes.

File Size
consolidated.safetensors 8.86GB
model.safetensors 8.86GB

Quantized and Converted Variants

→ Scroll horizontally to see all columns

Added Publisher Format Repository Smallest VRAM tier (build, est. memory)
2026-11-17 mradermacher GGUF mradermacher/Voxtral-Mini-4B-Realtime-Arabic-GGUF Q6_K 3.2GB (fits in 4GB VRAM)

File sizes of each build:

  • Available builds in mradermacher/Voxtral-Mini-4B-Realtime-Arabic-GGUF: Q2_K 1.4GB / Q3_K_S 1.5GB / Q3_K_M 1.7GB / Q3_K_L 1.8GB / IQ4_XS 1.8GB / Q4_K_S 1.9GB / Q4_K_M 2.0GB / Q5_K_S 2.3GB / Q5_K_M 2.3GB / Q6_K 2.6GB / Q8_0 3.4GB / F16 6.4GB

This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files.

Articles (the family’s own models first, then newest)

Published Model Type Article
2026-11-17 mistralai/Voxtral-Mini-4B-Realtime-Arabic Image, Video and Audio Voxtral-Mini-4B-Realtime-Arabic Speech Recognition Model: 4GB+ VRAM
2026-11-17 ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF Image, Video and Audio Voxtral-Mini-4B-Realtime-2602-GGUF Real-time ASR Model: 4GB+ VRAM

Repositories

Last updated 2026-11-17 (JST). Assembled by code from our article log; no text on this page is written by an AI model.