CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mistral / Voxtral-Mini-4B-Realtime-2602-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mistralSubject:

Voxtral-Mini-4B-Realtime-2602-GGUF

Date: 2026-11-14Commit: 0b0f7acSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model. Gguf weights, 16.1 GB in all. Published by ggml-org under Apache-2.0.

mistral16.1GBVoxtral-Mini-4B-Realtime-2602-GGUFggufpermissive
FactsParamsnot statedSize16.1 GBFormatsggufTaskautomatic speech recognitionLicenseApache-2.0From sourcepermissive
$ fw get ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF
# manifest sha256 097a0d8c7ca4… · 16.1 GB · 9 files
$ fw verify ./Voxtral-Mini-4B-Realtime-2602-GGUF ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF
From sourceHosted (signed)ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUFLast check: 2026-11-14 21:28 UTC
Run at homeGet help

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

Quantized of Voxtral-Mini-4B-Realtime-2602.

Works with

Run26Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.1 GB
Weights
2.55 GB (smallest of 3 GGUF variants)
Parameters
not stated
Formats
gguf
Task
automatic speech recognition
License
Apache-2.0 (permissive)
Files
9, each with a sha256
Publisher
ggml-org
Added
2026-11-14
Section
alt.freeweights.mistral
Lineage

Original release from the publisher.

Base model: mistralai/Voxtral-Mini-4B-Realtime-2602

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.co2026-11-14 21:28 UTCpassed

Model card

From the publisher at commit 0b0f7ac. Shown as plain text with links; images open at the publisher.

Voxtral-Mini-4B-Realtime-2602#

Run it in the Llama app: https://llama.app

Or from the terminal:

llama serve -hf ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF

This is a realtime (streaming) speech recognition model. See https://github.com/ggml-org/llama.cpp/pull/30629

Source models#

Important. This model is automatically converted using https://github.com/ggml-org/convert

Files

9 files · 16.1 GBWeights 2.55 GB (smallest of 3 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.92 KB5f9a3dd444c39bd247c33053f59c42e8464d15e9625b3646aa8c7a9511f6fa3c
.src_sha49 B79f690905a6616fa0c46d774ead8b293aed0be15c13709a667693367ba06d037
README.md616 B8dbc94579ba951c0289fae64d10789ee7d2f59b0420dd10a6380b7d36b8b28c8
Voxtral-Mini-4B-Realtime-2602-BF16.gguf6.88 GB0a8305a11c6250936a3ef18046861acbeb476781bc632c3d9e2718a56cc874c0
Voxtral-Mini-4B-Realtime-2602-Q4_K_M.gguf2.55 GBaa7a91fd78a896562642c61950887ec18c999425ab064bfc5ca9e64f8f5b29be
Voxtral-Mini-4B-Realtime-2602-Q8_0.gguf3.66 GBaa1df815ca5f95c0d964efef9661a138734f4419f68b86947feacdd19ea142d3
convert.log227 KB789c0266c35962208cf9c5aade22b122f4a8cac494159fd8b026a300d1cd3d81
mmproj-Voxtral-Mini-4B-Realtime-2602-BF16.gguf1.99 GB97520f6b498c9b6fe0963a31ed162845dede1cd0232d6cab139724f556c8abfe
mmproj-Voxtral-Mini-4B-Realtime-2602-Q8_0.gguf1.06 GBf28ae3e40f2b610c1c39b5c936ae854b73d0fc487518c6f69b76c22dbcea9ee3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0b0f7ac97a pinned now manifest updated, same commit2026-11-14 21:28 UTC9 files · 16.1 GB
0b0f7ac97a2026-11-14 21:28 UTC9 files · 16.1 GB

Use it

$ fw get ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF
# manifest sha256 097a0d8c7ca4… · 16.1 GB · 9 files
$ fw verify ./Voxtral-Mini-4B-Realtime-2602-GGUF ggml-org/Voxtral-Mini-4B-Realtime-2602-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/Voxtral-Mini-4B-Realtime-2602-GGUF.json --dir ./Voxtral-Mini-4B-Realtime-2602-GGUF $ python3 fw.py verify ./Voxtral-Mini-4B-Realtime-2602-GGUF ./ggml-org__Voxtral-Mini-4B-Realtime-2602-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF --revision 0b0f7ac97a2bc290053ec2339b70227c59ae6386 --local-dir ./Voxtral-Mini-4B-Realtime-2602-GGUF
llama.cppDownload one GGUF variant (Voxtral-Mini-4B-Realtime-2602-Q4_K_M, 2.55 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF --include "Voxtral-Mini-4B-Realtime-2602-Q4_K_M*" --local-dir ./Voxtral-Mini-4B-Realtime-2602-GGUF $ llama-server -m ./Voxtral-Mini-4B-Realtime-2602-GGUF/Voxtral-Mini-4B-Realtime-2602-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./Voxtral-Mini-4B-Realtime-2602-GGUF/Voxtral-Mini-4B-Realtime-2602-Q4_K_M.gguf\n' > Modelfile $ ollama create voxtral-mini-4b-realtime-2602-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. 2026-11-14
Text in
README.md
Text sha256
8dbc94579ba951c0289fae64d10789ee7d2f59b0420dd10a6380b7d36b8b28c8
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: Voxtral-Mini-4B-Realtime-2602-GGUFDate: 2026-11-14Commit: 0b0f7acSigned: 2DC28CC7B26A283B ✓
Upstream
ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF
Pinned commit
0b0f7ac97a2bc290053ec2339b70227c59ae6386
Manifest
Voxtral-Mini-4B-Realtime-2602-GGUF.json · .minisig
Manifest sha256
097a0d8c7ca4e0a608bf3c267ae26628abf6aa619a1c6cd8fbfc7eef7f222316
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:28 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF.json.minisig $ minisign -Vm Voxtral-Mini-4B-Realtime-2602-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/Voxtral-Mini-4B-Realtime-2602 · 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/Voxtral-Mini-4B-Realtime-2602-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Voxtral-Mini-4B-Realtime-2602-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/Voxtral-Mini-4B-Realtime-2602-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