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

DeepSeek-V4-Flash

Date: 2026-11-15Commit: f3b89cbSigned: 2DC28CC7B26A283B ✓

Text generation model with 50.6B parameters. Safetensors weights, 155 GB in all. Published by mlx-community under MIT.

50.6B params155GBDeepSeek-V4-Flashsafetensorspermissive
FactsParams50.6BSize155 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-V4-Flash
# manifest sha256 f3f6d1c34441… · 155 GB · 40 files
$ fw verify ./DeepSeek-V4-Flash mlx-community/DeepSeek-V4-Flash
From sourceHosted (signed)mlx-community/DeepSeek-V4-FlashLast check: 2026-11-15 05:14 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

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
155 GB
Weights
155 GB (safetensors)
Parameters
50.6B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
40, each with a sha256
Publisher
mlx-community
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 05:14 UTCpassed

Model card

From the publisher at commit f3b89cb. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-V4-Flash#

This 8-bit model mlx-community/DeepSeek-V4-Flash was converted to MLX format from deepseek-ai/DeepSeek-V4-Flash.

DeepSeek-V4-Flash is a Mixture-of-Experts model with 284B total parameters, 13B activated parameters, and a context length of 1M tokens. Refer to the original model card for more details on the model.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-V4-Flash")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

40 files · 155 GBWeights 155 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 40 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.09 KB483107a077a87f8ff02d16587f228e62c4c18869bbbb94285db1cf94e78d88ed
config.json2.21 KB7f49d78c9654babfa0d8218eb0f8d3c1a6ff893782bcad774a1481fa2c98d336
generation_config.json170 B5fccff80f55a4d455bbe516bdd552edf3e9623df95e99fbf2a3c3389fdf91af0
model-00001-of-00033.safetensors5.33 GBdb0fb40ffd6c2670634efcfe8d8c428361693442636d397a3184b7c480bcbf34
model-00002-of-00033.safetensors4.80 GB94d899cfb4429af55743b156584b47682a82a5b48fa39c812f90db9ce5305e4e
model-00003-of-00033.safetensors4.89 GBb7b5275c4b78a1ee053945d8578d68497f533209cc3fa2c4af4476167dbe9ebf
model-00004-of-00033.safetensors4.71 GB48b2b8af2932a1d7fc72c70620df185a3d954887345f9b097cae097159663101
model-00005-of-00033.safetensors4.73 GB273d07340b5f42f020ff2cac16395c4cb3a5ea281fcfc5e66255358ba6f4a624
model-00006-of-00033.safetensors4.88 GB84101e3814161b50899faa1d06a1157660d9265e22c1f3b7dd36ebfcfa786591
model-00007-of-00033.safetensors4.71 GB99d3fedd71be2cc7283529a55c659eb049c7109db99d52c44156c846f1bc1d67
model-00008-of-00033.safetensors4.73 GBd9131bfb2ea7772fc8bdfe5aa6a7cfb85ad0ef8e7050e9b745accc5a9c58e917
model-00009-of-00033.safetensors4.88 GBe898ccdaa9e6c425453508af7c65e488d8826fdbaf2961b7ad25e0ab0a01fc8f
model-00010-of-00033.safetensors4.71 GBa11ecaa6dc687c2bdc37e7429c2db57d69cd5b3029d7868166ca2a511313d6f0
model-00011-of-00033.safetensors4.73 GB0ecd6f6ddb1516fcf4f3e8cfe2e84310e1fd0e110ded60fdcb5c6e98efcf1a1c
model-00012-of-00033.safetensors4.88 GB190274daad0220f5af6a140483f23bdcec6dfce2ba2d285c78dbb42edb78c2c8
model-00013-of-00033.safetensors4.71 GB41769f57625e271c15e98abfc75cf89bb8bd7c4ae6cb9541cc6746fec0e0d690
model-00014-of-00033.safetensors4.73 GB8a5daab18433845a0c45b896a7471dd2e52b2612fac24e0f29c5e7fb031b0166
model-00015-of-00033.safetensors4.88 GB4114d4db50b8a89bed050305cec6de15775add0e3c263df0cfdb54025d0e9ab4
model-00016-of-00033.safetensors4.71 GB17fd0e1047e177b6abdec0b6ecc4d921953c266b7f0a45b1e635cc74a95f9a29
model-00017-of-00033.safetensors4.73 GBaef05c3bbf29b860bd105ecc3bb7e6f5f9f8b1301a54d3afa5538f4d6a2d7251
model-00018-of-00033.safetensors4.88 GB726afbcaf2a662b2bf47fb6bfa885a66c111590cd99354c6fcd2d203d3b13eb5
model-00019-of-00033.safetensors4.71 GBd12aec4eb71ea6582d963309f1488256832f44bb0da570a1420986960476e5bb
model-00020-of-00033.safetensors4.73 GBc8cf17ae8e2632ca17973619b4f5495a39fdfc3b268cc493d78da14db650fa25
model-00021-of-00033.safetensors4.88 GB702fc71922564bd1023abc9c6148479e7707079ea94fcf4f0a359c056661b7ec
model-00022-of-00033.safetensors4.71 GBb5ea22ac32a0ac6093bbefb005a7f7ab3fd760d3fe3e2961dcb06d0707a37f67
model-00023-of-00033.safetensors4.73 GBde428f0c20d8e9f9960dccc8317ceea7fed7fe6ad3c56f594b29efe38837d9a4
model-00024-of-00033.safetensors4.88 GBfd37469dc18490f804c2e4da256c499ee7948352ae949b20a3b77defb505719c
model-00025-of-00033.safetensors4.71 GB152a290deb23d702815fe6e9ca88be66f6cafd24e9fc11c0a44654f9e9fecccb
model-00026-of-00033.safetensors4.73 GBdb6567c856ae807029d5d4eb09d748b765934e15c48c2f80f5f878b4de2b5e14
model-00027-of-00033.safetensors4.88 GBaf2e82d9b2a02d891bdcd21fedcf73b97a82081848dfba05f96a6507d409d3b6
model-00028-of-00033.safetensors4.71 GB06c03ad09199ef1dbb263e19f10e346c4e780e34abd26ee1ec5b93066556cae1
model-00029-of-00033.safetensors4.73 GB66c88d57f02e53b2564bbd5663dba134bbf396ef0877ba3a8a341b738f968807
model-00030-of-00033.safetensors4.88 GB4e2885fabb9cc9488fd915822ffe6691332759fe5b7d73118d3adf2bf8f5df2e
model-00031-of-00033.safetensors4.71 GB6d6c9396c4fdcb6043aa8f0ea36d5710012c990c2682cc5277142cb0e14e72d3
model-00032-of-00033.safetensors4.73 GB51d781122ca30e0f947f10b5a99d7edd61ed18582e72de48dafaea43e89ea163
model-00033-of-00033.safetensors1.73 GB3828314ee7f865532c467ae2a9a642794d7258a2eb39a19de9870304fb3beba4
model.safetensors.index.json216 KBed86b1b8d5a1fb5c5af438bbf92bce60aaa4a1d208aa5a57c7dabcf9f786647e
tokenizer.json10.1 MB8421075aceec0741baf15179b6c337f443f9029e53ea88d8c1e909dd0d69b70b
tokenizer_config.json397 B21aa165d554e2c2f252a49730b71962edc15c36bbfa4b090ab7bd3340a2fa549
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f3b89cb425 pinned now2026-11-15 05:14 UTC40 files · 155 GB

Use it

$ fw get mlx-community/DeepSeek-V4-Flash
# manifest sha256 f3f6d1c34441… · 155 GB · 40 files
$ fw verify ./DeepSeek-V4-Flash mlx-community/DeepSeek-V4-Flash
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Flash.json --dir ./DeepSeek-V4-Flash $ python3 fw.py verify ./DeepSeek-V4-Flash ./mlx-community__DeepSeek-V4-Flash.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-V4-Flash --revision f3b89cb425ca69d045b8321869a64032356345a6 --local-dir ./DeepSeek-V4-Flash
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/DeepSeek-V4-Flash", revision="f3b89cb425ca69d045b8321869a64032356345a6") model = AutoModelForCausalLM.from_pretrained("mlx-community/DeepSeek-V4-Flash", revision="f3b89cb425ca69d045b8321869a64032356345a6", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-V4-Flash --revision f3b89cb425ca69d045b8321869a64032356345a6

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
483107a077a87f8ff02d16587f228e62c4c18869bbbb94285db1cf94e78d88ed
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V4-FlashDate: 2026-11-15Commit: f3b89cbSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-V4-Flash
Pinned commit
f3b89cb425ca69d045b8321869a64032356345a6
Manifest
DeepSeek-V4-Flash.json · .minisig
Manifest sha256
f3f6d1c344415af1743907d3f487a18d5b39184a6335765bbc649461ea76df8a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

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

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