CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.kimi / Kimi-VL-A3B-Thinking-2506-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.kimiSubject:

Kimi-VL-A3B-Thinking-2506-GGUF

Date: 2026-11-15Commit: e7dcd09Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 93.8 GB in all. Published by ggml-org under MIT.

kimi93.8GBKimi-VL-A3B-Thinking-2506-GGUFggufpermissive
FactsParamsnot statedSize93.8 GBFormatsggufTasknot taggedLicenseMITFrom sourcepermissive
$ fw get ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF
# manifest sha256 dbe4cd2600c0… · 93.8 GB · 9 files
$ fw verify ./Kimi-VL-A3B-Thinking-2506-GGUF ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF
From sourceHosted (signed)ggml-org/Kimi-VL-A3B-Thinking-2506-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 Kimi-VL-A3B-Thinking-2506.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
93.8 GB
Weights
10.5 GB (smallest of 4 GGUF variants)
Parameters
not stated
Formats
gguf
Task
not tagged
License
MIT (permissive)
Files
9, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.kimi
Lineage

Original release from the publisher.

Base model: moonshotai/Kimi-VL-A3B-Thinking-2506

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

From the publisher at commit e7dcd09. Shown as plain text with links; images open at the publisher.

Original model: https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506

Supported added in this PR: https://github.com/ggml-org/llama.cpp/pull/15458

Files

9 files · 93.8 GBWeights 10.5 GB (smallest of 4 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes2.04 KB68f76e8397157b0531eef897137690e3bab68f71c4bb97357567b45164494bc7
Kimi-VL-A3B-Thinking-2506-Q4_K_M.gguf10.5 GB72253d82d21c546587139dfd12597d491c25a13c6540d2ce18ca1581967338c5
Kimi-VL-A3B-Thinking-2506-Q8_0.gguf17.0 GBffcfd257855ee9f16243d8d16b4d74fcb106d3dc1fd65f466d1c089bf320b377
Kimi-VL-A3B-Thinking-2506-bf16.gguf31.9 GB952f3faa372910984089d16db89927548c0f11dab36ee21f57ea79df23b32378
Kimi-VL-A3B-Thinking-2506-f16.gguf31.9 GB00dc49807794d7368aca96898a6bf6f5e4bbe60fa539ddc0464a8e531b8f08f5
README.md214 Bbd157d743b23e9df6f7767f7fc6758850d5f6dbbb5fecd4fdcf8c7b21a214ed5
mmproj-Kimi-VL-A3B-Thinking-2506-Q8_0.gguf618 MB5af5e5fc0ad5e2348f5227ddfa97e9241d453020c149dbe0e920ed603189ca15
mmproj-Kimi-VL-A3B-Thinking-2506-bf16.gguf907 MBfc9b4043c3cd9a4649eec121b688e0e3bf609f6b3f836e45282f8a34f3ffee39
mmproj-Kimi-VL-A3B-Thinking-2506-f16.gguf905 MB1386854a5031970a92ec458ddcc2dfce575f28edf6463643e50ac2f008068fb3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e7dcd09333 pinned now2026-11-15 04:49 UTC9 files · 93.8 GB

Use it

$ fw get ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF
# manifest sha256 dbe4cd2600c0… · 93.8 GB · 9 files
$ fw verify ./Kimi-VL-A3B-Thinking-2506-GGUF ggml-org/Kimi-VL-A3B-Thinking-2506-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/Kimi-VL-A3B-Thinking-2506-GGUF.json --dir ./Kimi-VL-A3B-Thinking-2506-GGUF $ python3 fw.py verify ./Kimi-VL-A3B-Thinking-2506-GGUF ./ggml-org__Kimi-VL-A3B-Thinking-2506-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF --revision e7dcd093335f922a057772febc7ab27eda985b40 --local-dir ./Kimi-VL-A3B-Thinking-2506-GGUF
llama.cppDownload one GGUF variant (Kimi-VL-A3B-Thinking-2506-Q4_K_M, 10.5 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF --include "Kimi-VL-A3B-Thinking-2506-Q4_K_M*" --local-dir ./Kimi-VL-A3B-Thinking-2506-GGUF $ llama-server -m ./Kimi-VL-A3B-Thinking-2506-GGUF/Kimi-VL-A3B-Thinking-2506-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./Kimi-VL-A3B-Thinking-2506-GGUF/Kimi-VL-A3B-Thinking-2506-Q4_K_M.gguf\n' > Modelfile $ ollama create kimi-vl-a3b-thinking-2506-gguf -f Modelfile
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model moonshotai/Kimi-VL-A3B-Thinking-2506: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
bd157d743b23e9df6f7767f7fc6758850d5f6dbbb5fecd4fdcf8c7b21a214ed5
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.kimiSubject: Kimi-VL-A3B-Thinking-2506-GGUFDate: 2026-11-15Commit: e7dcd09Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF
Pinned commit
e7dcd093335f922a057772febc7ab27eda985b40
Manifest
Kimi-VL-A3B-Thinking-2506-GGUF.json · .minisig
Manifest sha256
dbe4cd2600c0b2bcd9bfa9a257080865354323aecabd60cf5e3cd8083eb09ed6
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/Kimi-VL-A3B-Thinking-2506-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF.json.minisig $ minisign -Vm Kimi-VL-A3B-Thinking-2506-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

moonshotai/Kimi-VL-A3B-Thinking-2506 · 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/Kimi-VL-A3B-Thinking-2506-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Kimi-VL-A3B-Thinking-2506-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF

Related models

All of alt.freeweights.kimi →
From: laion <huggingface.co/laion>Subject: kimi-k2-r2egym_sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Subject: kimi-k2t-freelancer-32ep-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k
From: laion <huggingface.co/laion>Subject: Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k