alt.freeweights.mistral / Ministral-3-3B-Reasoning-2512-GGUF

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mistralSubject:

Ministral-3-3B-Reasoning-2512-GGUF

Date: 2026-11-15Commit: 6373de8Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 4.10 GB in all. Published by ggml-org under Apache-2.0.

mistral

4.10GBMinistral-3-3B-Reasoning-2512-GGUFggufpermissive

FactsParamsnot statedSize4.10 GBFormatsggufTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
# manifest sha256 0e797d101992… · 4.10 GB · 4 files
$ fw verify ./Ministral-3-3B-Reasoning-2512-GGUF ggml-org/Ministral-3-3B-Reasoning-2512-GGUF

From sourceHosted (signed)ggml-org/Ministral-3-3B-Reasoning-2512-GGUFLast check: 2026-11-15 05:08 UTC

Run at home Get help

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

Quantized of Ministral-3-3B-Reasoning-2512.

Works with

Run13 Convert1 Evaluate13 Scan12 Apps62

Runs with

Ranked by fit to this model (gguf), then by GitHub stars.

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile KoboldCpp PocketPal AI llama-swap ik_llama.cpp RamaLama

Show all 13

Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 4.10 GB
Weights: 3.65 GB (GGUF)
Parameters: not stated
Formats: gguf
Task: image text to text
License: Apache-2.0 (permissive)
Files: 4, each with a sha256
Publisher: ggml-org
Added: 2026-11-15
Section: alt.freeweights.mistral

Lineage

Original release from the publisher.

Base model: mistralai/Ministral-3-3B-Reasoning-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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:08 UTC	passed

Model card

From the publisher at commit 6373de8. Shown as plain text with links; images open at the publisher.

Ministral-3-3B-Reasoning-2512-GGUF#

This model is converted from mistralai/Ministral-3-3B-Reasoning-2512 to GGUF using convert_hf_to_gguf.py

To use it:

llama-server -hf ggml-org/Ministral-3-3B-Reasoning-2512-GGUF

Files

4 files · 4.10 GBWeights 3.65 GB (GGUF). Sizes and sha256 from the signed manifest.

Hide all 4 files with their sha256

File	Size	sha256
.gitattributes	1.68 KB	82156e9b87ce3eaeaf69f75166c542ea432d835236c9b2b865c1b1f502060656
Ministral-3-3B-Reasoning-2512-Q8_0.gguf	3.65 GB	8bb60ece89db5969890c282613d7bfd93f3d1c0a72a37fc579be1ae99eb2eca2
README.md	406 B	2635e2beba5c009835dc6818a94f4cb232d05030b272dcc88c18ba8cf1d07d40
mmproj-Ministral-3-3B-Reasoning-2512-Q8_0.gguf	448 MB	f0e34ffcc888dfe1d05d6615426d6a5674b27d2e55a4043a1ec3964febaae0f7

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
6373de865c pinned now	2026-11-15 05:08 UTC	4 files · 4.10 GB

Use it

$ fw get ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
# manifest sha256 0e797d101992… · 4.10 GB · 4 files
$ fw verify ./Ministral-3-3B-Reasoning-2512-GGUF ggml-org/Ministral-3-3B-Reasoning-2512-GGUF

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/Ministral-3-3B-Reasoning-2512-GGUF.json --dir ./Ministral-3-3B-Reasoning-2512-GGUF
$ python3 fw.py verify ./Ministral-3-3B-Reasoning-2512-GGUF ./ggml-org__Ministral-3-3B-Reasoning-2512-GGUF.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Ministral-3-3B-Reasoning-2512-GGUF --revision 6373de865cde31bb48488a22684512a1997867be --local-dir ./Ministral-3-3B-Reasoning-2512-GGUF

llama.cppDownload one GGUF variant (Ministral-3-3B-Reasoning-2512-Q8_0, 3.65 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Ministral-3-3B-Reasoning-2512-GGUF --include "Ministral-3-3B-Reasoning-2512-Q8_0*" --local-dir ./Ministral-3-3B-Reasoning-2512-GGUF
$ llama-server -m ./Ministral-3-3B-Reasoning-2512-GGUF/Ministral-3-3B-Reasoning-2512-Q8_0.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./Ministral-3-3B-Reasoning-2512-GGUF/Ministral-3-3B-Reasoning-2512-Q8_0.gguf\n' > Modelfile
$ ollama create ministral-3-3b-reasoning-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: 2635e2beba5c009835dc6818a94f4cb232d05030b272dcc88c18ba8cf1d07d40
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:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mistralSubject: Ministral-3-3B-Reasoning-2512-GGUFDate: 2026-11-15Commit: 6373de8Signed: 2DC28CC7B26A283B ✓

Upstream: ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
Pinned commit: 6373de865cde31bb48488a22684512a1997867be
Manifest: Ministral-3-3B-Reasoning-2512-GGUF.json · .minisig
Manifest sha256: 0e797d1019922f8b887deefd0221be5f3adae254fa03887ff6e6f426649899c2
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:08 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/Ministral-3-3B-Reasoning-2512-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ggml-org/Ministral-3-3B-Reasoning-2512-GGUF.json.minisig
$ minisign -Vm Ministral-3-3B-Reasoning-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-3-3B-Reasoning-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 ggml-org/Ministral-3-3B-Reasoning-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-3-3B-Reasoning-2512-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ggml-org/Ministral-3-3B-Reasoning-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