CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mistral / Ministral-3-8B-Instruct-2512-GGUF
From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject:

Ministral-3-8B-Instruct-2512-GGUF

Date: 2026-11-15Commit: 0102285Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 38.1 GB in all. Published by mistralai under Apache-2.0.

mistral38.1GBMinistral-3-8B-Instruct-2512-GGUFggufpermissive
FactsParamsnot statedSize38.1 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get mistralai/Ministral-3-8B-Instruct-2512-GGUF
# manifest sha256 3b0eef1751c6… · 38.1 GB · 7 files
$ fw verify ./Ministral-3-8B-Instruct-2512-GGUF mistralai/Ministral-3-8B-Instruct-2512-GGUF
From sourceHosted (signed)mistralai/Ministral-3-8B-Instruct-2512-GGUFLast check: 2026-11-15 04:37 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Ministral-3-8B-Instruct-2512.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
38.1 GB
Weights
5.20 GB (smallest of 4 GGUF variants)
Parameters
not stated
Formats
gguf
Task
not tagged
License
Apache-2.0 (permissive)
Files
7, each with a sha256
Publisher
mistralai
Added
2026-11-15
Section
alt.freeweights.mistral
Lineage

Original release from the publisher.

Base model: mistralai/Ministral-3-8B-Instruct-2512

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:37 UTCpassed

Model card

From the publisher at commit 0102285. Shown as plain text with links; images open at the publisher.

Ministral 3 8B Instruct 2512 GGUF#

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

This model includes different quantization levels of the instruct post-trained version in GGUF, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 8B can even be deployed locally, capable of fitting in 12GB of VRAM in FP8, and less if further quantized.

Learn more in our blog post and paper.

Key Features#

Ministral 3 8B consists of two main architectural components:

  • 8.4B Language Model
  • 0.4B Vision Encoder

The Ministral 3 8B Instruct model offers the following capabilities:

  • Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
  • Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
  • System Prompt: Maintains strong adherence and support for system prompts.
  • Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
  • Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
  • Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
  • Large Context Window: Supports a 256k context window.

We recommend deploying with the following best practices:

  • System Prompt: Define a clear environment and use case, including guidance on how to effectively leverage tools in agentic systems.
  • Sampling Parameters: Use a temperature below 0.1 for daily-driver and production environments ; Higher temperatures may be explored for creative use cases - developers are encouraged to experiment with alternative settings.
  • Tools: Keep the set of tools well-defined and limit their number to the minimum required for the use case - Avoiding overloading the model with an excessive number of tools.
  • Vision: When deploying with vision capabilities, we recommend maintaining an aspect ratio close to 1:1 (width-to-height) for images. Avoiding the use of overly thin or wide images - crop them as needed to ensure optimal performance.

License#

This model is licensed under the Apache 2.0 License.

You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.

Files

7 files · 38.1 GBWeights 5.20 GB (smallest of 4 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 7 files with their sha256
FileSizesha256
.gitattributes1.91 KB15f1e31b032a924dd235f69935ae358fde910cb297fc8ada884be59617d60cda
Ministral-3-8B-Instruct-2512-BF16-mmproj.gguf858 MBe799380f596d152ff4026a72d409ecc89c96cd437676804bc3f2ab3bd6b486ec
Ministral-3-8B-Instruct-2512-BF16.gguf17.0 GBfa785e6a56f240dacbc451ea4aaab501d11f5903005903cec6e0ba11c30e3357
Ministral-3-8B-Instruct-2512-Q4_K_M.gguf5.20 GB33e7a72cf5e6e2cfc2f2847075acc013d68bba023e35310cef86b5cf8fdca761
Ministral-3-8B-Instruct-2512-Q5_K_M.gguf6.06 GB7a5454127ec772e2389f0e71a77fedb88b83d4366d8a69facd0cfd0898f04d35
Ministral-3-8B-Instruct-2512-Q8_0.gguf9.03 GBbd0ca58473b64618df4d08c1410cc25c910ca84e647833ebaf099e0fc0523b45
README.md3.17 KBedf52a7d939a3a7368258e3d81a2c7224134e04a22f820ad6d97ec213be20fd5
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0102285ad7 pinned now2026-11-15 04:37 UTC7 files · 38.1 GB

Use it

$ fw get mistralai/Ministral-3-8B-Instruct-2512-GGUF
# manifest sha256 3b0eef1751c6… · 38.1 GB · 7 files
$ fw verify ./Ministral-3-8B-Instruct-2512-GGUF mistralai/Ministral-3-8B-Instruct-2512-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-GGUF.json --dir ./Ministral-3-8B-Instruct-2512-GGUF $ python3 fw.py verify ./Ministral-3-8B-Instruct-2512-GGUF ./mistralai__Ministral-3-8B-Instruct-2512-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-8B-Instruct-2512-GGUF --revision 0102285ad796bd99af90f58de616092e5630e970 --local-dir ./Ministral-3-8B-Instruct-2512-GGUF
llama.cppDownload one GGUF variant (Ministral-3-8B-Instruct-2512-Q4_K_M, 5.20 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-8B-Instruct-2512-GGUF --include "Ministral-3-8B-Instruct-2512-Q4_K_M*" --local-dir ./Ministral-3-8B-Instruct-2512-GGUF $ llama-server -m ./Ministral-3-8B-Instruct-2512-GGUF/Ministral-3-8B-Instruct-2512-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./Ministral-3-8B-Instruct-2512-GGUF/Ministral-3-8B-Instruct-2512-Q4_K_M.gguf\n' > Modelfile $ ollama create ministral-3-8b-instruct-2512-gguf -f Modelfile
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
edf52a7d939a3a7368258e3d81a2c7224134e04a22f820ad6d97ec213be20fd5
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject: Ministral-3-8B-Instruct-2512-GGUFDate: 2026-11-15Commit: 0102285Signed: 2DC28CC7B26A283B ✓
Upstream
mistralai/Ministral-3-8B-Instruct-2512-GGUF
Pinned commit
0102285ad796bd99af90f58de616092e5630e970
Manifest
Ministral-3-8B-Instruct-2512-GGUF.json · .minisig
Manifest sha256
3b0eef1751c6a16e2038362543595ed818e6454ae6ba603c6516afa5bc81d92e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:37 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-8B-Instruct-2512-GGUF.json.minisig $ minisign -Vm Ministral-3-8B-Instruct-2512-GGUF.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

mistralai/Ministral-3-8B-Instruct-2512 · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-8B-Instruct-2512-GGUF
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Ministral-3-8B-Instruct-2512-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF

Related models

All of alt.freeweights.mistral →
From: bartowski <huggingface.co/bartowski>Subject: alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF
From: microsoft <huggingface.co/microsoft>Subject: chatbench-mistral-7b
From: NousResearch <huggingface.co/NousResearch>Subject: DeepHermes-3-Mistral-24B-Preview
From: mistralai <huggingface.co/mistralai>Subject: Devstral-Small-2-24B-Instruct-2512
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit