CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-V4.1-Flash-1017-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4.1-Flash-1017-GGUF

Date: 2026-11-14Commit: 6bc1f89Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 651 GB in all. Published by ggml-org under MIT.

deepseek651GBDeepSeek-V4.1-Flash-1017-GGUFggufpermissive
FactsParamsnot statedSize651 GBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/DeepSeek-V4.1-Flash-1017-GGUF
# manifest sha256 8e15d8a6c2da… · 651 GB · 20 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-GGUF ggml-org/DeepSeek-V4.1-Flash-1017-GGUF
From sourceHosted (signed)ggml-org/DeepSeek-V4.1-Flash-1017-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-V4.1-Flash-1017.

Works with

Run13Convert1Evaluate13Scan12Apps62

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
651 GB
Weights
7.91 GB (smallest of 4 GGUF variants)
Parameters
not stated
Formats
gguf
Task
image text to text
License
MIT (permissive)
Files
20, 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-V4.1-Flash-1017

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 6bc1f89. Shown as plain text with links; images open at the publisher.

DeepSeek-V4.1-Flash-1017#

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

Or from the terminal:

llama serve -hf ggml-org/DeepSeek-V4.1-Flash-1017-GGUF
Source models#
Notes#
  • Includes a Q8_0 mmproj for the vision encoder.
  • The Q2_K quantization keeps the routed down experts in MXFP4.
  • The Q2_K_S quantization converts the routed down experts to Q2_K.
  • The Engram KV tensors are Q8_0 and the PLE table is IQ4_NL.
  • The Q2 models do not use an imatrix calibration.
TODOs#
  • add info

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

Files

20 files · 651 GBWeights 7.91 GB (smallest of 4 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 20 files with their sha256
FileSizesha256
.gitattributes2.88 KBdea8f6b062f2d60781620bc931bce8a4e8cb47d581c69e9379fc1e2e226d0f1f
.src_sha49 B71a7290552a301a0237134c64ff8695774659d01e281e1c4fb1800fc64d1055d
DeepSeek-V4.1-Flash-1017-Q2_K-00001-of-00006.gguf5.78 MB3e3804c31203832b572e45b635830edeb381e4b4733e17eabd1ea4000f54c934
DeepSeek-V4.1-Flash-1017-Q2_K-00002-of-00006.gguf73.8 GBf24e6c124e8d7765e644072c6c455dbd162b0f4f11d26167ac53f7127bf33334
DeepSeek-V4.1-Flash-1017-Q2_K-00003-of-00006.gguf72.9 GBcb9aed84b34a0eed64bc6c63f4477c849a3bc67cf13dd88de5e07ffad0e0f2bf
DeepSeek-V4.1-Flash-1017-Q2_K-00004-of-00006.gguf68.4 GBc651c95d80fb5139019f60268c6529258f4edaf3993703914b1729116614f95b
DeepSeek-V4.1-Flash-1017-Q2_K-00005-of-00006.gguf111 GB7b04016a36e58ed17c814ebdb5c15406aa96f6a4c41cc6e1ea5579ca592d8a0f
DeepSeek-V4.1-Flash-1017-Q2_K-00006-of-00006.gguf9.05 GBc4754167b34f594b72c0a863118e5e008daadcd5ac666bae4df557e8439c5844
DeepSeek-V4.1-Flash-1017-Q2_K_S-00001-of-00006.gguf5.78 MB3e3804c31203832b572e45b635830edeb381e4b4733e17eabd1ea4000f54c934
DeepSeek-V4.1-Flash-1017-Q2_K_S-00002-of-00006.gguf60.9 GBc22eaf93afe1c66a983d8ef15087ddb881b6d9f7514ecfabf2f6520c46428ff9
DeepSeek-V4.1-Flash-1017-Q2_K_S-00003-of-00006.gguf60.9 GB440fb6329fa5fea17ad7c439502f360af82319e16f681a981322b2ae39fe89e1
DeepSeek-V4.1-Flash-1017-Q2_K_S-00004-of-00006.gguf56.5 GB2f1c4d173a6e16cf59a5e76dbd0ccb18706f9e631615e54d30d6096b0952c597
DeepSeek-V4.1-Flash-1017-Q2_K_S-00005-of-00006.gguf111 GB7b04016a36e58ed17c814ebdb5c15406aa96f6a4c41cc6e1ea5579ca592d8a0f
DeepSeek-V4.1-Flash-1017-Q2_K_S-00006-of-00006.gguf9.05 GBc4754167b34f594b72c0a863118e5e008daadcd5ac666bae4df557e8439c5844
README.md799 B6b92f637500cf50f639ae94306ba8ad1d1c5cbfb61d90a059447f6346a72b455
convert.log675 KB87eae9f5a10fd0ce798e468874258ed2db97a2226cf3b1df5679d0634e338c60
dspark-DeepSeek-V4.1-Flash-1017-BF16.gguf8.51 GB00a02b0e4f476d87003cd0f92338848e26c1eb04888ee32dc4746828a4e0f09a
dspark-DeepSeek-V4.1-Flash-1017-MXFP4.gguf7.91 GB0d4afadf88e85f459e14c242c93b104913676e309cd24ab4abd6e8eec6812602
mmproj-DeepSeek-V4.1-Flash-1017-BF16.gguf972 MB0fdc4b7693f287e9665940cf42bd39c546ffe4f0def89c569d7d0e45d60d2df1
mmproj-DeepSeek-V4.1-Flash-1017-Q8_0.gguf518 MB279a98efcd540fea43c1f5d855c3c486e1de6688a45bf78710cbea4cb1c48bdd
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6bc1f89d4b pinned now manifest updated, same commit2026-11-14 21:28 UTC20 files · 651 GB
6bc1f89d4b2026-11-14 21:28 UTC20 files · 651 GB

Use it

$ fw get ggml-org/DeepSeek-V4.1-Flash-1017-GGUF
# manifest sha256 8e15d8a6c2da… · 651 GB · 20 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-GGUF ggml-org/DeepSeek-V4.1-Flash-1017-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-V4.1-Flash-1017-GGUF.json --dir ./DeepSeek-V4.1-Flash-1017-GGUF $ python3 fw.py verify ./DeepSeek-V4.1-Flash-1017-GGUF ./ggml-org__DeepSeek-V4.1-Flash-1017-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/DeepSeek-V4.1-Flash-1017-GGUF --revision 6bc1f89d4b7ae7125ce9a795ea20ef6b5d0e8099 --local-dir ./DeepSeek-V4.1-Flash-1017-GGUF
llama.cppDownload one GGUF variant (dspark-DeepSeek-V4.1-Flash-1017-MXFP4, 7.91 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/DeepSeek-V4.1-Flash-1017-GGUF --include "dspark-DeepSeek-V4.1-Flash-1017-MXFP4*" --local-dir ./DeepSeek-V4.1-Flash-1017-GGUF $ llama-server -m ./DeepSeek-V4.1-Flash-1017-GGUF/dspark-DeepSeek-V4.1-Flash-1017-MXFP4.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-V4.1-Flash-1017-GGUF/dspark-DeepSeek-V4.1-Flash-1017-MXFP4.gguf\n' > Modelfile $ ollama create deepseek-v4.1-flash-1017-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
6b92f637500cf50f639ae94306ba8ad1d1c5cbfb61d90a059447f6346a72b455
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-V4.1-Flash-1017-GGUFDate: 2026-11-14Commit: 6bc1f89Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/DeepSeek-V4.1-Flash-1017-GGUF
Pinned commit
6bc1f89d4b7ae7125ce9a795ea20ef6b5d0e8099
Manifest
DeepSeek-V4.1-Flash-1017-GGUF.json · .minisig
Manifest sha256
8e15d8a6c2daad62be2f02d8faf8c56581e132c7b95905f44fc2028617cc69c2
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-V4.1-Flash-1017-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/DeepSeek-V4.1-Flash-1017-GGUF.json.minisig $ minisign -Vm DeepSeek-V4.1-Flash-1017-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-V4.1-Flash-1017 · 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-V4.1-Flash-1017-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-V4.1-Flash-1017-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/DeepSeek-V4.1-Flash-1017-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