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

DeepSeek-V4-Flash-GGUF

Date: 2026-11-15Commit: 8878219Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 381 GB in all. Published by ggml-org under MIT.

deepseek381GBDeepSeek-V4-Flash-GGUFggufpermissive
FactsParamsnot statedSize381 GBFormatsggufTasktext generationLicenseMITFrom sourcepermissive
$ fw get ggml-org/DeepSeek-V4-Flash-GGUF
# manifest sha256 b8f362b1f0e1… · 381 GB · 12 files
$ fw verify ./DeepSeek-V4-Flash-GGUF ggml-org/DeepSeek-V4-Flash-GGUF
From sourceHosted (signed)ggml-org/DeepSeek-V4-Flash-GGUFLast check: 2026-11-15 05:01 UTC
Get help

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

Quantized of DeepSeek-V4-Flash.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
381 GB
Weights
4.73 GB (smallest of 5 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
MIT (permissive)
Files
12, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

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

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 05:01 UTCpassed

Model card

From the publisher at commit 8878219. Shown as plain text with links; images open at the publisher.

DeepSeek-V4-Flash#

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

Or from the terminal:

llama serve -hf ggml-org/DeepSeek-V4-Flash-GGUF
Source models#
Notes#
  • 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

12 files · 381 GBWeights 4.73 GB (smallest of 5 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes2.20 KB792f525b6d619140ac934a7c92d38163aaa1d4dc56c6c1989fee1af4712a08c0
.src_sha49 B4516809f0f33d3a3bd42fc72d1a0257b459e71aae0a58c5229a981041490dca3
DeepSeek-V4-Flash-MXFP4-00001-of-00002.gguf5.25 MBaa52d7c0ba08350780e05d74f98f2e67be03dd6862f5878545d754ed56557dae
DeepSeek-V4-Flash-MXFP4-00002-of-00002.gguf155 GBe541dcb8f2595553512d625d112fa00e376377173f49b8ac075de46179727a6b
DeepSeek-V4-Flash-Q2_K-00001-of-00002.gguf5.25 MBaa52d7c0ba08350780e05d74f98f2e67be03dd6862f5878545d754ed56557dae
DeepSeek-V4-Flash-Q2_K-00002-of-00002.gguf117 GB0dba57a26036cc218452fb12651c91b2a1527bbdcfccd2a11bad7254d4a1a10a
DeepSeek-V4-Flash-Q2_K_S-00001-of-00002.gguf5.25 MBaa52d7c0ba08350780e05d74f98f2e67be03dd6862f5878545d754ed56557dae
DeepSeek-V4-Flash-Q2_K_S-00002-of-00002.gguf98.6 GB87f4ce3f0c00d2c412cadd42af86d6c7558b20ae305a614efe76c08e4c224f8c
README.md533 Bf1629cb2389dcaeebb2d5c57705cbe06c45a17a7ecc5b44d174d85f7c922af9a
convert.log868 KB191f79fdb75b8eb1c708747fe3160f31dbff01f91b120003edacedf6015e76e2
mtp-DeepSeek-V4-Flash-BF16.gguf5.73 GB245ad97fb0170d1e1ee167bc8ba083e6a776f55e2034020084783d1ba183d1df
mtp-DeepSeek-V4-Flash-MXFP4.gguf4.73 GBc87353fc47ece6b00710f6af785a1bfdd513f812e1f60eafcb038348a84e5494
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
88782195bf pinned now2026-11-15 05:01 UTC12 files · 381 GB

Use it

$ fw get ggml-org/DeepSeek-V4-Flash-GGUF
# manifest sha256 b8f362b1f0e1… · 381 GB · 12 files
$ fw verify ./DeepSeek-V4-Flash-GGUF ggml-org/DeepSeek-V4-Flash-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-GGUF.json --dir ./DeepSeek-V4-Flash-GGUF $ python3 fw.py verify ./DeepSeek-V4-Flash-GGUF ./ggml-org__DeepSeek-V4-Flash-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-GGUF --revision 88782195bf893ff2d6a28902ea36a96ba708e2fb --local-dir ./DeepSeek-V4-Flash-GGUF
llama.cppDownload one GGUF variant (mtp-DeepSeek-V4-Flash-MXFP4, 4.73 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/DeepSeek-V4-Flash-GGUF --include "mtp-DeepSeek-V4-Flash-MXFP4*" --local-dir ./DeepSeek-V4-Flash-GGUF $ llama-server -m ./DeepSeek-V4-Flash-GGUF/mtp-DeepSeek-V4-Flash-MXFP4.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-V4-Flash-GGUF/mtp-DeepSeek-V4-Flash-MXFP4.gguf\n' > Modelfile $ ollama create deepseek-v4-flash-gguf -f Modelfile

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
f1629cb2389dcaeebb2d5c57705cbe06c45a17a7ecc5b44d174d85f7c922af9a
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-GGUFDate: 2026-11-15Commit: 8878219Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/DeepSeek-V4-Flash-GGUF
Pinned commit
88782195bf893ff2d6a28902ea36a96ba708e2fb
Manifest
DeepSeek-V4-Flash-GGUF.json · .minisig
Manifest sha256
b8f362b1f0e15fe429ab2b525fdbb68342bfaf4432c74c75f795937cc336c5e0
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:01 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/DeepSeek-V4-Flash-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/DeepSeek-V4-Flash-GGUF.json.minisig $ minisign -Vm DeepSeek-V4-Flash-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 · 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-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-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/DeepSeek-V4-Flash-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