CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.llama / ultravox-v0_5-llama-3_2-1b-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.llamaSubject:

ultravox-v0_5-llama-3_2-1b-GGUF

Date: 2026-11-15Commit: 5390c7cSigned: 2DC28CC7B26A283B ✓

Audio text to text model. Gguf weights, 3.50 GB in all. Published by ggml-org under MIT.

llama3.50GBultravox-v0_5-llama-3_2-1b-GGUFggufpermissive
FactsParamsnot statedSize3.50 GBFormatsggufTaskaudio text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF
# manifest sha256 bbc995fdc4a9… · 3.50 GB · 5 files
$ fw verify ./ultravox-v0_5-llama-3_2-1b-GGUF ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF
From sourceHosted (signed)ggml-org/ultravox-v0_5-llama-3_2-1b-GGUFLast check: 2026-11-15 04:49 UTC
Run at homeGet help

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

Quantized of ultravox-v0_5-llama-3_2-1b.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.50 GB
Weights
808 MB (smallest of 2 GGUF variants)
Parameters
not stated
Formats
gguf
Task
audio text to text
License
MIT (permissive)
Files
5, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.llama
Lineage

Original release from the publisher.

Base model: fixie-ai/ultravox-v0_5-llama-3_2-1b

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 04:49 UTCpassed

Model card

No model card stored here.No README was stored for this model. Read the publisher's page: https://huggingface.co/ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF

Files

5 files · 3.50 GBWeights 808 MB (smallest of 2 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 5 files with their sha256
FileSizesha256
.gitattributes1.97 KBb177ced5b35cf4235078b431c73f4f9ce24ca64596e288942478f9c5da594611
Llama-3.2-1B-Instruct-Q4_K_M.gguf808 MB6f85a640a97cf2bf5b8e764087b1e83da0fdb51d7c9fab7d0fece9385611df83
Llama-3.2-1B-Instruct-Q8_0.gguf1.32 GB432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3
README.md103 B82e00c9707182c143e6032a6e7d4a7a57bd18d16e85d0a4b81ee112d63e7b5af
mmproj-ultravox-v0_5-llama-3_2-1b-f16.gguf1.37 GBb34dde1835752949d6b960528269af93c92fec91c61ea0534fcc73f96c1ed8b2
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
5390c7c41c pinned now2026-11-15 04:49 UTC5 files · 3.50 GB

Use it

$ fw get ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF
# manifest sha256 bbc995fdc4a9… · 3.50 GB · 5 files
$ fw verify ./ultravox-v0_5-llama-3_2-1b-GGUF ggml-org/ultravox-v0_5-llama-3_2-1b-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/ultravox-v0_5-llama-3_2-1b-GGUF.json --dir ./ultravox-v0_5-llama-3_2-1b-GGUF $ python3 fw.py verify ./ultravox-v0_5-llama-3_2-1b-GGUF ./ggml-org__ultravox-v0_5-llama-3_2-1b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF --revision 5390c7c41cbd6f261f7f205fc0c5ae61bbdca650 --local-dir ./ultravox-v0_5-llama-3_2-1b-GGUF
llama.cppDownload one GGUF variant (Llama-3.2-1B-Instruct-Q4_K_M, 808 MB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF --include "Llama-3.2-1B-Instruct-Q4_K_M*" --local-dir ./ultravox-v0_5-llama-3_2-1b-GGUF $ llama-server -m ./ultravox-v0_5-llama-3_2-1b-GGUF/Llama-3.2-1B-Instruct-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./ultravox-v0_5-llama-3_2-1b-GGUF/Llama-3.2-1B-Instruct-Q4_K_M.gguf\n' > Modelfile $ ollama create ultravox-v0-5-llama-3-2-1b-gguf -f Modelfile
Run at home

License

Name
MIT License
Id
MIT
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
82e00c9707182c143e6032a6e7d4a7a57bd18d16e85d0a4b81ee112d63e7b5af
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.llamaSubject: ultravox-v0_5-llama-3_2-1b-GGUFDate: 2026-11-15Commit: 5390c7cSigned: 2DC28CC7B26A283B ✓
Upstream
ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF
Pinned commit
5390c7c41cbd6f261f7f205fc0c5ae61bbdca650
Manifest
ultravox-v0_5-llama-3_2-1b-GGUF.json · .minisig
Manifest sha256
bbc995fdc4a96c735de07a1fbdb3af63a89df384b6d131433f043dbd19744842
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:49 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF.json.minisig $ minisign -Vm ultravox-v0_5-llama-3_2-1b-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

fixie-ai/ultravox-v0_5-llama-3_2-1b · 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/ultravox-v0_5-llama-3_2-1b-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. ultravox-v0_5-llama-3_2-1b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF

Related models

All of alt.freeweights.llama →
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V-gguf
From: BAAI <huggingface.co/BAAI>Subject: Bunny-v1_1-Llama-3-8B-V
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b-bnb-4bit
From: BAAI <huggingface.co/BAAI>Subject: Infinity-Instruct-3M-0613-Llama3-70B