CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / LongCat-Flash-Chat-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject:

LongCat-Flash-Chat-GGUF

Date: 2026-11-15Commit: c9123b8Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 154 GB in all. Published by ggml-org under MIT.

text154GBLongCat-Flash-Chat-GGUFggufpermissive
FactsParamsnot statedSize154 GBFormatsggufTasknot taggedLicenseMITFrom sourcepermissive
$ fw get ggml-org/LongCat-Flash-Chat-GGUF
# manifest sha256 5996bb2c9d93… · 154 GB · 14 files
$ fw verify ./LongCat-Flash-Chat-GGUF ggml-org/LongCat-Flash-Chat-GGUF
From sourceHosted (signed)ggml-org/LongCat-Flash-Chat-GGUFLast check: 2026-11-15 05:24 UTC
Get help

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

Quantized of LongCat-Flash-Chat.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

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

Original release from the publisher.

Base model: meituan-longcat/LongCat-Flash-Chat

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 05:24 UTCpassed

Model card

From the publisher at commit c9123b8. Shown as plain text with links; images open at the publisher.
QuantSizeMixturePPL1-(Mean PPL(Q)/PPL(base))KLD
Q8_0557.39 GiB (8.51 BPW)Q8_03.275749 ± 0.017863+0.2918%0.003764 ± 0.000045
IQ1_S106.19 GiB (1.62 BPW)IQ1_S11.010332 ± 0.077291+237.0971%1.331246 ± 0.004350

Image: kld_graph Image: ppl_graph

Files

14 files · 154 GBWeights 844 MB (smallest of 2 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes2.05 KBf755e7c085522760c6b94537fc735816458bda9372251f13d5d5c125b658b6ab
IQ1_S/LongCat-Flash-Chat-IQ1_S-00001-of-00004.gguf5.48 MB0d7f720450971dd9dd45e2610ccb90b3035ffaf644d0f0cfe7f3bd3637b8884f
IQ1_S/LongCat-Flash-Chat-IQ1_S-00002-of-00004.gguf49.8 GB5772b1e790b7661c1fc5a34a9271e4168aac7fdbdd4ac76dabfd7cf9424d99e9
IQ1_S/LongCat-Flash-Chat-IQ1_S-00003-of-00004.gguf49.8 GBcdf568ba42666c8ac8b5955183ba7d8f4e6eb73c20c75287799030df98dd3d42
IQ1_S/LongCat-Flash-Chat-IQ1_S-00004-of-00004.gguf14.4 GB00b19f8b1cb1c250a3a60ee8ef6a8a72e67db82999038135cef19dce3782ea2e
README.md715 B8a0366d437e0ac4a681e35301f7d7f72d5a5ad51ee4977fd7e4ecc764fd130d8
imatrix.gguf844 MBa4dd1bfb54188a2525bdcb3b1db1c84e877c2b6ed98c72c7e26fd19473248a8a
kld_data/01_kld_vs_filesize.png122 KBe4c15240f37b382404fd315ea2762a3c7d06ce9b48940fa91d36c730b79f1d98
kld_data/02_ppl_vs_filesize.png134 KB101e0cb606494d9f3990d4cd5e00438ee2641e6bec6c3875a6403d83b16ff155
kld_data/LongCat-Flash-Chat-BF16-512ctx-wiki.test.raw.bin39.0 GBd421afc00292b6073684aa7c819711bfe5e30438cf50335becc42f3308a767fc
kld_data/aes_sedai/LongCat-Flash-Chat-IQ1_S.md102 KBd016ee5c508e9d90b449bd317dfc36fff5f0f30365c7bde62aae997aa432d67e
kld_data/aes_sedai/LongCat-Flash-Chat-Q8_0.md181 KB5c8ee17345d84dda02fe0e44dbc68edb19dc3efb2d4f18e4a31ea0331458ff6d
kld_data/llm_quantization_data.csv15.0 KB976974a985878f9acf66be1675a5811737a16b2831983cc829eebe43e7b85629
kld_data/wiki.test.raw1.29 MB173c87a53759e0201f33e0ccf978e510c2042d7f2cb78229d9a50d79b9e7dd08
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c9123b8567 pinned now2026-11-15 05:24 UTC14 files · 154 GB

Use it

$ fw get ggml-org/LongCat-Flash-Chat-GGUF
# manifest sha256 5996bb2c9d93… · 154 GB · 14 files
$ fw verify ./LongCat-Flash-Chat-GGUF ggml-org/LongCat-Flash-Chat-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/LongCat-Flash-Chat-GGUF.json --dir ./LongCat-Flash-Chat-GGUF $ python3 fw.py verify ./LongCat-Flash-Chat-GGUF ./ggml-org__LongCat-Flash-Chat-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LongCat-Flash-Chat-GGUF --revision c9123b8567a97317304ad665d884eb1c8dfd4c1e --local-dir ./LongCat-Flash-Chat-GGUF
llama.cppDownload one GGUF variant (imatrix, 844 MB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LongCat-Flash-Chat-GGUF --include "imatrix*" --local-dir ./LongCat-Flash-Chat-GGUF $ llama-server -m ./LongCat-Flash-Chat-GGUF/imatrix.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./LongCat-Flash-Chat-GGUF/imatrix.gguf\n' > Modelfile $ ollama create longcat-flash-chat-gguf -f Modelfile

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model meituan-longcat/LongCat-Flash-Chat: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
8a0366d437e0ac4a681e35301f7d7f72d5a5ad51ee4977fd7e4ecc764fd130d8
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.textSubject: LongCat-Flash-Chat-GGUFDate: 2026-11-15Commit: c9123b8Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/LongCat-Flash-Chat-GGUF
Pinned commit
c9123b8567a97317304ad665d884eb1c8dfd4c1e
Manifest
LongCat-Flash-Chat-GGUF.json · .minisig
Manifest sha256
5996bb2c9d93ef603f72fd4675ea6a11f4fc37630d77eea791689427664f5221
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/LongCat-Flash-Chat-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/LongCat-Flash-Chat-GGUF.json.minisig $ minisign -Vm LongCat-Flash-Chat-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

meituan-longcat/LongCat-Flash-Chat · 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/LongCat-Flash-Chat-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. LongCat-Flash-Chat-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/LongCat-Flash-Chat-GGUF

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B