CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-V4-Flash-Vision-Exp-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4-Flash-Vision-Exp-GGUF

Date: 2026-11-14Commit: 67ec949Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 394 GB in all. Published by ggml-org under MIT.

deepseek394GBDeepSeek-V4-Flash-Vision-Exp-GGUFggufpermissive
FactsParamsnot statedSize394 GBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
# manifest sha256 e9ad4e8afea6… · 394 GB · 14 files
$ fw verify ./DeepSeek-V4-Flash-Vision-Exp-GGUF ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
From sourceHosted (signed)ggml-org/DeepSeek-V4-Flash-Vision-Exp-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 DeepSeek-V4-Flash-Vision-Exp.

Works with

Run13Convert1Evaluate13Scan12Apps62

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
394 GB
Weights
10.8 GB (smallest of 5 GGUF variants)
Parameters
not stated
Formats
gguf
Task
image text to text
License
MIT (permissive)
Files
14, each with a sha256
Publisher
ggml-org
Added
2026-11-14
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Base model: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

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 67ec949. Shown as plain text with links; images open at the publisher.

DeepSeek-V4-Flash-Vision-Exp#

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

Or from the terminal:

llama serve -hf ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
Source models#
Notes#
  • Includes a Q8_0 mmproj for the vision encoder.
  • Currently, the Q2 models do not use an imatrix calibration due to lack of one.

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

Files

14 files · 394 GBWeights 10.8 GB (smallest of 5 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes2.39 KBc338c87bb640a941475b8656a147f3d4aae8c835064f11b9f20a10484b46f5d5
.src_sha49 B2452123c13e980655033c3c3a3398b99d662d0ad085e484e2c9aabd83aec8ab6
DeepSeek-V4-Flash-Vision-Exp-MXFP4-00001-of-00002.gguf5.25 MB8ea7f241199a24661953316751e90f392c3652c4456e1a2029033528a51b5566
DeepSeek-V4-Flash-Vision-Exp-MXFP4-00002-of-00002.gguf155 GBef3585c3a366b05fe83779cd9081e1c37c8bdbf783f276cd13a2319cec366a80
DeepSeek-V4-Flash-Vision-Exp-Q2_K-00001-of-00002.gguf5.25 MB8ea7f241199a24661953316751e90f392c3652c4456e1a2029033528a51b5566
DeepSeek-V4-Flash-Vision-Exp-Q2_K-00002-of-00002.gguf117 GB8046a31425268c7777cadfa9c678a74e2a4017dff5585e6e501f80d7e6a0d2ce
DeepSeek-V4-Flash-Vision-Exp-Q2_K_S-00001-of-00002.gguf5.25 MB8ea7f241199a24661953316751e90f392c3652c4456e1a2029033528a51b5566
DeepSeek-V4-Flash-Vision-Exp-Q2_K_S-00002-of-00002.gguf98.6 GB777b08a2bd625734fde45f0fd4f00dec2b69e35b11675528de13972df1360127
README.md629 Bfafefb135d58e5db7b01ccfcc4c3e525e9586575dbc712e93c995d326ec4bf5e
convert.log967 KB6f6e901688de4eff4a3badc433fcd3f3b408d9063d456668592c072cf172b116
dspark-DeepSeek-V4-Flash-Vision-Exp-BF16.gguf10.9 GBc6758719c24c9e290382e7d4b839e918ea5533bd5bf9eb5d3ce43e767e10de15
dspark-DeepSeek-V4-Flash-Vision-Exp-MXFP4.gguf10.8 GBf69029b484272b8d9ef7cfc9bb0d6cba40a3ddaf6683f4cddd466a706af6cb6c
mmproj-DeepSeek-V4-Flash-Vision-Exp-BF16.gguf934 MB17ff6b7bb26ffab434ec89847595eecff895ff4cc5fcfc2777a21e993e3a9be5
mmproj-DeepSeek-V4-Flash-Vision-Exp-Q8_0.gguf498 MB87c904c77a6bef59538a05c151ae57bf1b527cb4d509c48be0e5d2341ba15552
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
67ec949d11 pinned now manifest updated, same commit2026-11-14 21:28 UTC14 files · 394 GB
67ec949d112026-11-14 21:28 UTC14 files · 394 GB

Use it

$ fw get ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
# manifest sha256 e9ad4e8afea6… · 394 GB · 14 files
$ fw verify ./DeepSeek-V4-Flash-Vision-Exp-GGUF ggml-org/DeepSeek-V4-Flash-Vision-Exp-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/DeepSeek-V4-Flash-Vision-Exp-GGUF.json --dir ./DeepSeek-V4-Flash-Vision-Exp-GGUF $ python3 fw.py verify ./DeepSeek-V4-Flash-Vision-Exp-GGUF ./ggml-org__DeepSeek-V4-Flash-Vision-Exp-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF --revision 67ec949d115974254a7c715672d05c5bce8fef4e --local-dir ./DeepSeek-V4-Flash-Vision-Exp-GGUF
llama.cppDownload one GGUF variant (dspark-DeepSeek-V4-Flash-Vision-Exp-MXFP4, 10.8 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF --include "dspark-DeepSeek-V4-Flash-Vision-Exp-MXFP4*" --local-dir ./DeepSeek-V4-Flash-Vision-Exp-GGUF $ llama-server -m ./DeepSeek-V4-Flash-Vision-Exp-GGUF/dspark-DeepSeek-V4-Flash-Vision-Exp-MXFP4.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-V4-Flash-Vision-Exp-GGUF/dspark-DeepSeek-V4-Flash-Vision-Exp-MXFP4.gguf\n' > Modelfile $ ollama create deepseek-v4-flash-vision-exp-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. 2026-11-14
Text in
README.md
Text sha256
fafefb135d58e5db7b01ccfcc4c3e525e9586575dbc712e93c995d326ec4bf5e
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.deepseekSubject: DeepSeek-V4-Flash-Vision-Exp-GGUFDate: 2026-11-14Commit: 67ec949Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
Pinned commit
67ec949d115974254a7c715672d05c5bce8fef4e
Manifest
DeepSeek-V4-Flash-Vision-Exp-GGUF.json · .minisig
Manifest sha256
e9ad4e8afea62f21f769b4611a0b6eb56a0f6165d3c18d0b8039bf09d294599b
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/DeepSeek-V4-Flash-Vision-Exp-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF.json.minisig $ minisign -Vm DeepSeek-V4-Flash-Vision-Exp-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

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp · 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/DeepSeek-V4-Flash-Vision-Exp-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V4-Flash-Vision-Exp-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF

Related models

All of alt.freeweights.deepseek →
From: timm <huggingface.co/timm>Subject: deepseek_vit_412m.deepseek_v4_1_flash
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3-0324-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3.1-GGUF
From: mlx-community <huggingface.co/mlx-community>Subject: deepseek-ai-DeepSeek-V4-Flash-8bit