CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-V4-Flash-0731-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4-Flash-0731-GGUF

Date: 2026-11-14Commit: e5d9d96Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 156 GB in all. Published by lmstudio-community under MIT.

deepseek156GBDeepSeek-V4-Flash-0731-GGUFggufpermissive
FactsParamsnot statedSize156 GBFormatsggufTasktext generationLicenseMITFrom sourcepermissive
$ fw get lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
# manifest sha256 644ece896ca2… · 156 GB · 6 files
$ fw verify ./DeepSeek-V4-Flash-0731-GGUF lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
From sourcelmstudio-community/DeepSeek-V4-Flash-0731-GGUFLast check: 2026-11-14 06:28 UTC
Runs withllama.cppOllama
OverviewFilesUse itLicenseProvenance

Overview

Size
156 GB
Weights
156 GB (GGUF)
Parameters
not stated
Formats
gguf
Task
text generation
License
MIT (permissive)
Files
6, each with a sha256
Publisher
lmstudio-community
Added
2026-11-14
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Base model: deepseek-ai/DeepSeek-V4-Flash-0731

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 06:28 UTCpassed

Files

6 files · 156 GBWeights 156 GB (GGUF). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes2.19 KB7a646ee3b3e800e2dbc2a059477ccca398d07a85536473c11ebc306182957af7
DeepSeek-V4-Flash-0731-MXFP4-00001-of-00004.gguf39.9 GB810cb08cd6b6a2d53c7dee42666e1021a95412b27236911d4bbc52c1d76b9780
DeepSeek-V4-Flash-0731-MXFP4-00002-of-00004.gguf39.9 GB81677f78cf0c9174c15bab7af6ec80ffdf3842c2f126429b9fad464b956c08f7
DeepSeek-V4-Flash-0731-MXFP4-00003-of-00004.gguf39.9 GBb3456e914dd112d14d06681e7e7fdcf260e21c86e1d0f501b2e5b4463a0cf481
DeepSeek-V4-Flash-0731-MXFP4-00004-of-00004.gguf36.6 GB48d91e57fcd4834371ad02561d42eed6159294a10c7fa3d64eb1330a2f0002d8
README.md2.18 KBa3bc4f85ec3e55ea2198a3e7080566f7f8a47397f036027cea51c83820cc526c

Use it

$ fw get lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
# manifest sha256 644ece896ca2… · 156 GB · 6 files
$ fw verify ./DeepSeek-V4-Flash-0731-GGUF lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/DeepSeek-V4-Flash-0731-GGUF.json --dir ./DeepSeek-V4-Flash-0731-GGUF $ python3 fw.py verify ./DeepSeek-V4-Flash-0731-GGUF ./lmstudio-community__DeepSeek-V4-Flash-0731-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSeek-V4-Flash-0731-GGUF --revision e5d9d9689670fd2bb83dcca8dcdf15a5f50bf670 --local-dir ./DeepSeek-V4-Flash-0731-GGUF
llama.cppDownload one GGUF variant (DeepSeek-V4-Flash-0731-MXFP4, 156 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSeek-V4-Flash-0731-GGUF --include "DeepSeek-V4-Flash-0731-MXFP4*" --local-dir ./DeepSeek-V4-Flash-0731-GGUF $ llama-server -m ./DeepSeek-V4-Flash-0731-GGUF/DeepSeek-V4-Flash-0731-MXFP4-00001-of-00004.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-V4-Flash-0731-GGUF/DeepSeek-V4-Flash-0731-MXFP4-00001-of-00004.gguf\n' > Modelfile $ ollama create deepseek-v4-flash-0731-gguf -f Modelfile
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Text in
README.md
Text sha256
a3bc4f85ec3e55ea2198a3e7080566f7f8a47397f036027cea51c83820cc526c
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V4-Flash-0731-GGUFDate: 2026-11-14Commit: e5d9d96Signed: 2DC28CC7B26A283B ✓
Upstream
lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
Pinned commit
e5d9d9689670fd2bb83dcca8dcdf15a5f50bf670
Manifest
DeepSeek-V4-Flash-0731-GGUF.json · .minisig
Manifest sha256
644ece896ca2a84f579bf3d4fd576b29a967db27f77a8229f025bec023618c59
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:28 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/DeepSeek-V4-Flash-0731-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/DeepSeek-V4-Flash-0731-GGUF.json.minisig $ minisign -Vm DeepSeek-V4-Flash-0731-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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/DeepSeek-V4-Flash-0731-GGUF
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V4-Flash-0731-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/lmstudio-community/DeepSeek-V4-Flash-0731-GGUF

Related models

All of alt.freeweights.deepseek →
From: unsloth <huggingface.co/unsloth>Subject: DeepSeek-V4.1-Flash-1017-GGUF
From: deepseek-ai <huggingface.co/deepseek-ai>Subject: DeepSeek-V4-Flash-0731
From: deepseek-ai <huggingface.co/deepseek-ai>Subject: DeepSeek-V4.1-Flash-1017
From: ISTA-DASLab <huggingface.co/ISTA-DASLab>Subject: DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF