CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-R1-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-R1-4bit

Date: 2026-11-15Commit: 5aa5895Signed: 2DC28CC7B26A283B ✓

Model with 671B parameters. Safetensors weights, 420 GB in all. Published by mlx-community under MIT.

671B params420GBDeepSeek-R1-4bitsafetensorspermissive
FactsParams671BSize420 GBFormatssafetensorsTasknot taggedLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-R1-4bit
# manifest sha256 196975c13cd2… · 420 GB · 95 files
$ fw verify ./DeepSeek-R1-4bit mlx-community/DeepSeek-R1-4bit
From sourceHosted (signed)mlx-community/DeepSeek-R1-4bitLast 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-R1.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
420 GB
Weights
420 GB (safetensors)
Parameters
671B
Formats
safetensors
Task
not tagged
License
MIT (permissive)
Files
95, 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-R1

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 5aa5895. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-R1-4bit#

The Model mlx-community/DeepSeek-R1-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1 using mlx-lm version 0.21.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-4bit")

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

95 files · 420 GBWeights 420 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 95 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md761 B1efd1862e40cb7cc27cacde791d6b5ae8a1fcbd9fab89fa4c087b67ee5933d53
config.json1.85 KB733fd3f2150ef95c0551da57b5e2cec487cab941ed2d9d93ebd0dc95a74ef8b1
model-00001-of-00088.safetensors4.14 GB7e1a9ad1ae3dc9a82c5680e4df8419cbd0c716e2b4efbb25db389da9a301d6e5
model-00002-of-00088.safetensors4.85 GB212d45f261464422936665176ce84df517a68683e7a09d88742d19eb1e1b678f
model-00003-of-00088.safetensors4.70 GB6c330182e4b0b999e14f88ec95a8d0e9be94baac5b808cc379713f185645b8fd
model-00004-of-00088.safetensors4.85 GBc9b95f158884ea9b00b3114639d94a293f22c5829a9036dca38e3575cb639aff
model-00005-of-00088.safetensors4.85 GBc7fa0425c84328012b8e1b818e928e93f5f41c7968b40015a250be381a8db3f6
model-00006-of-00088.safetensors4.70 GB59ee6280c1bb7b50c395fd88054b0d87068f9a8d32b7eee26ad5a706a634ee9c
model-00007-of-00088.safetensors4.85 GBd97f974564c367594f0ea1bb438b1a13f75470149ab55dbd3944bf59ff51b4dc
model-00008-of-00088.safetensors4.85 GB712c76c4175044191f965d5d523eb96030c643eaff28554967e7033efc193799
model-00009-of-00088.safetensors4.70 GB835ea13d926bc247ac70c15e891144b04823c0b5f0e21f0acba499a5673f5182
model-00010-of-00088.safetensors4.85 GBbfa2b036c4713302b85c2b21308e01f5c85a2e58fdac6bc7a3b13b6ccaab5885
model-00011-of-00088.safetensors4.85 GBb5fee492133ad0f4a1d60bec513bcd2fd792beda239057e433f037913e83ca8e
model-00012-of-00088.safetensors4.70 GBc3fc27225c7a6b1815fd40559b01e9cf7324ae8f12d9bb48723ace95254ed912
model-00013-of-00088.safetensors4.85 GB2868c8f1dd2ce51b9de18e638ba6c312cf7155c9bf1adac72db0d5aeddbda557
model-00014-of-00088.safetensors4.85 GB00a09c7a00c8539a654eae40e60da4ba8deaac79109659eb52decd79b2392b5f
model-00015-of-00088.safetensors4.70 GBb594393f5ff4047248c7ab48260a061d04bb77223b0c6b95037da94a03385b04
model-00016-of-00088.safetensors4.85 GB282c73e9bc1da16fd2e1ec3b1bcd4ecf782d4b9d96305da063d0d08bc5d7692f
model-00017-of-00088.safetensors4.85 GB8b9b3d4b28c034bfd033267f96f4a80bfcca330d081b699fb82b627be392baed
model-00018-of-00088.safetensors4.70 GBf2ada8ced123a450b641a6fdfa0bd8237724d0456de93f262835257544d670f1
model-00019-of-00088.safetensors4.85 GBf8e984344a80029ab2e99fcaccfc86266e605dcb6219b65cb0eccf41fdade2f6
model-00020-of-00088.safetensors4.85 GB5a08d3e1cef5edd2b597cd3efaec7ee569dc0de916aa1b46fcfa9a0c543e5f5d
model-00021-of-00088.safetensors4.70 GB41c3fff651eb02748125e2e2748a7db01a2524013640a2e60b2ac49902411d2b
model-00022-of-00088.safetensors4.85 GB28b06c7b553fc2542a0ea4fa3b0f9eb43b701fda69f51ce7c7b50f6bca42019c
model-00023-of-00088.safetensors4.85 GB2d24e642b37e0eb080da776a9247a460f7075493cb7d9223db4930404653d030
model-00024-of-00088.safetensors4.70 GB73b4898b9302a8e15acdbcd5c2340a24dbafea096a4e701b040117c5f3959976
model-00025-of-00088.safetensors4.85 GB982c38a7c155583671ad8a97a925be54cf75d66fa3973f70ecfe5c93ef3870d8
model-00026-of-00088.safetensors4.85 GB2d6274f9a44f06275d73991a7afb552c6eb24588d8e4c93a4d19e6a5c6494983
model-00027-of-00088.safetensors4.70 GBb1779352d6a7f313473cc9a19b8e8d7eeecee843dd08f329bd10421bf65c7a12
model-00028-of-00088.safetensors4.85 GB1d71b175b8c3b27ebbe4410475fd9642e24349ed096051c26a9f50b3d81981df
model-00029-of-00088.safetensors4.85 GB0ca477f933ccef4897adb044a298d244ed25fa4ff2f362919d220b9446dac4f3
model-00030-of-00088.safetensors4.70 GB6c2183b03e2043f8453dd4cf8de4202862415aa2b89323f9c887b8cbb8c540c3
model-00031-of-00088.safetensors4.85 GB29caa25c6808fd43f4972e42278cbed7427425cff7a5911757f7d555b8fd5b74
model-00032-of-00088.safetensors4.85 GB6c9920044ccf8437b46ff827b6cb0b1d281329eff0d54c319b07d6bff53d118d
model-00033-of-00088.safetensors4.70 GB75cbad40518282888d8378222704f410c874391c1e012c69ce8fb81321252495
model-00034-of-00088.safetensors4.85 GB74a9e1cbc19a7bd07a980a63471296fe201b3e7487278b5147cad5ad87a5c49d
model-00035-of-00088.safetensors4.85 GB32dec2fc27150baaaa13b33c0cca40eeed32323de3e229a25519f1ecdabd9a5b
model-00036-of-00088.safetensors4.70 GBbfaead94a1faf27c4fd8b4a6e5418e3ea672f9fdbfaa0e1fb2433299c2f09f4d
model-00037-of-00088.safetensors4.85 GB5734bc734ee090d28edcba8be0181aa7a74779e4aff5092e48ef9807ebf07192
model-00038-of-00088.safetensors4.85 GBb45c1e799f39894142db25a082c11a33f5f484fc8c6c59e00ef9350e45e6638e
model-00039-of-00088.safetensors4.70 GBa7cbb8623216a76634f2cc3c140ff9f6f0ce1dd247c63c2d1670880a6c6b3fe7
model-00040-of-00088.safetensors4.85 GBa6dc12d88249ef32382c530557e145049b02fe26d1b714206fece5d449551ad4
model-00041-of-00088.safetensors4.85 GB959d96d060596d90e5e494c25429c3070940c9dc3fd76d2002db8622a3cf224a
model-00042-of-00088.safetensors4.70 GB42b63dc25a11421ba5a562521c741944819b04fae54c1242ed63f00ad0af5e19
model-00043-of-00088.safetensors4.85 GB1c4eb5ad5aa3eba836a7e4367967decab272a1b478a61a50229b915d94355e5a
model-00044-of-00088.safetensors4.85 GBaffe4c9156c6c631bcf8fefff22af829d48f9fdda9a3d3adac2ed0d9e3afde0a
model-00045-of-00088.safetensors4.70 GB129d1794b40eed71307a591fd38946c538141d2d15175654f2a9ec6a8cf0ca30
model-00046-of-00088.safetensors4.85 GB2e76827e32577fac5f8bece6edaff3d3c61e6bd9a88642eef5a1a8896616c28b
model-00047-of-00088.safetensors4.85 GB964ebc9e587814ae9105042028d75e42230db98325f8404a75f9ac97c9daa230
model-00048-of-00088.safetensors4.70 GB8de92fa42b4492d36f4ba96a8990adb6e1bf7cd7392e88a8f976b19ad91dda95
model-00049-of-00088.safetensors4.85 GBc5c26b853bba53b774627e0d672fd43288aeee6ac5833f4bae2bb06fab421855
model-00050-of-00088.safetensors4.85 GBb4590d76bd979af02c4c316c32e277903b207e14a211dd9311400f7bb64cb3ad
model-00051-of-00088.safetensors4.70 GB7a6da866125444e98f69aae90c9174c7ca4af55b54be66d4a4c1cd2e04abdab0
model-00052-of-00088.safetensors4.85 GBc60fdbb2046030e800499cd09fb2f1c74fd9114d8ce1dea439b64d49d9ecb7fb
model-00053-of-00088.safetensors4.85 GB074f3c4f8f6a26a9350f36051437a7cf2b53592efe8a8ffe60eec99c1ae74299
model-00054-of-00088.safetensors4.70 GBde03cdb7442f6a0ef7899f9730f4aaeb4e0294f93107cf5ac7b31e332838c6de
model-00055-of-00088.safetensors4.85 GB2bc84b83ef66346fdda4777da02adfa647308ce7ffe7a9f6fa10b9be8c7f4061
model-00056-of-00088.safetensors4.85 GB3df97641d13a1072100b71e1e388b4a03fbf16e612946e0536497f64b9190571
model-00057-of-00088.safetensors4.70 GB5c6f8ce8cf2650905410623513d2cdc47f233dcb69099ae782fb4eb7414a0793
model-00058-of-00088.safetensors4.85 GB5a373b2fac4fed370f4e536f44eff8bbb1a7eca65d78357a22e5b49e3d626956
model-00059-of-00088.safetensors4.85 GBe2ccb2f6c2bd6200e8465eb048f0633411837f4cfaade037c862c82ee18d696b
model-00060-of-00088.safetensors4.70 GB2ea9a0da2c6752c8082d087f14dc88c382863349d393b8e1047bd048522d79f0
model-00061-of-00088.safetensors4.85 GBfa2102cb639cb17b56a9e8e4a45e1a7bfe158e8f2f2c830be556da60209babe9
model-00062-of-00088.safetensors4.85 GB88ed9db8b828efae08cdacde8103c5f7d074c672bf398fee6c7cbaad328d090f
model-00063-of-00088.safetensors4.70 GB4181b654e5ccc39b7de3bdfff241c08c77224c6f80ca1f9de0250b1b41c3b07b
model-00064-of-00088.safetensors4.85 GB77a4b362ce60b720ed11aa10bee723e1cd72fc72437dbc0baa47d5f0e7d1385e
model-00065-of-00088.safetensors4.85 GB4ee141b5aad3fd41a03bf3de5a2715085029442f714cb2aeaf1536ceae4aecb9
model-00066-of-00088.safetensors4.70 GB01a8cf74c8472e278804b17a286a13d6cc1202c72130fca1a404d098b73bdc3c
model-00067-of-00088.safetensors4.85 GB8ff15679596e916ec00692f9b16fe004c0dcd960824f5240de139cd3e3443b09
model-00068-of-00088.safetensors4.85 GBde5a240a145aa43aa3bcb3c912ebf7bc07532f628c401dadb273818099ee46d9
model-00069-of-00088.safetensors4.70 GBae95f28122d525706e2ec91c22b1f04ca50544c3fbfb7225de1a3d86776d4ca8
model-00070-of-00088.safetensors4.85 GB3b3706da9d9fb92fb01ad4f610cc309b38da85d868d08138c776fb61584051cf
model-00071-of-00088.safetensors4.85 GB680ade389e9bdb73758e2ace3b895168555d93cf034fc488043ab351b0431858
model-00072-of-00088.safetensors4.70 GB52ca2bda1ebbaba87a575139821de55135197f8ae2ab37ffc32f54b5bcb6ecb6
model-00073-of-00088.safetensors4.85 GBf9af85f0d9922f55ce3edfa6d1b42d30aedf912930f601ab8ecc6d23dfeae84f
model-00074-of-00088.safetensors4.85 GBc4b95b3db172633df0c3c60fe3e1e1ea1e6bb2414740e43779180c6522c9fd6d
model-00075-of-00088.safetensors4.70 GB184ea73b73a312fa250303a2bc3638f19716d63a06411933aaa6ad1701fb0298
model-00076-of-00088.safetensors4.85 GB9ecb8d31404dc2c4b8457c2ed9ab136118fb1e9b720e5db9dbe12b82bde57af9
model-00077-of-00088.safetensors4.85 GBbee31f7b826c3cd50dddc12b0ceeb1e190ecad837666287d360f562df7fed2f2
model-00078-of-00088.safetensors4.70 GB43a42a510b8758b47a33edf8b0555887e855335f60fca8acee5377bf9b4d92ba
model-00079-of-00088.safetensors4.85 GB77e11b3195668104196cce96210d8c85bcc3cb63ec7bb6a5d128714eac376f84
model-00080-of-00088.safetensors4.85 GB3381f5c7ffdebbef67df859bc57272bc43fc6f9a40d593c2ff405779ea61e624
model-00081-of-00088.safetensors4.70 GB038a4c1ad41694936cbf52bb21b1afb45affbc17f5f288bd57c98e7c0c1373dc
model-00082-of-00088.safetensors4.85 GBd0c1098ce737c828ad47fe2b52feefc4e8327be8a819a9b7d008c3bd249d5492
model-00083-of-00088.safetensors4.85 GBa35a468f478c1567a581cf7b03ac6d5f55fd765c023b25a40bd1470448e3ccfd
model-00084-of-00088.safetensors4.70 GB3617a2a43a7f4fad2dc5f398fe910069f11bb1489de0a97e4ad97e0d774a2995
model-00085-of-00088.safetensors4.85 GB8e57efa0fe0c7702f59749170ca9ce7bf94c3cbfd4760c227b08322ebbbbc669
model-00086-of-00088.safetensors4.85 GBd4a14e264c2473a2abdd9c99f710796c9f11a81658bddb5a28d063609b17fa10
model-00087-of-00088.safetensors4.70 GB349e8336d67d65e254713b8cd25e2cc92e5b1af16d3457b520a1c4ff79534020
model-00088-of-00088.safetensors2.96 GBdeb69be5c1367a9cfdd191ce9e0e688db269337276918f00795d51fb86586312
model.safetensors.index.json219 KBa7e3cbf32be01183ed6f08ef76bba0b2ce80d4f58379c94ad7b66d7dc14d77c9
special_tokens_map.json485 B59cda48bbe8bab9d61ffb410e6e3c07b6d98bff73cee7c88ff8b51f95f21ab1c
tokenizer.json9.98 MBce20a7877bec9454dd611bc4e9116b7db765594f78524bd94edbaab422eddf02
tokenizer_config.json166 KB245509f8e347fed0073fb6d831865117f5b02182f5cd275cf60eaa9c9e2ca4d3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
5aa5895999 pinned now2026-11-15 05:01 UTC95 files · 420 GB

Use it

$ fw get mlx-community/DeepSeek-R1-4bit
# manifest sha256 196975c13cd2… · 420 GB · 95 files
$ fw verify ./DeepSeek-R1-4bit mlx-community/DeepSeek-R1-4bit
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-R1-4bit.json --dir ./DeepSeek-R1-4bit $ python3 fw.py verify ./DeepSeek-R1-4bit ./mlx-community__DeepSeek-R1-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-4bit --revision 5aa58959991bd42ce9c0eb634b1aff00a3410426 --local-dir ./DeepSeek-R1-4bit

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model deepseek-ai/DeepSeek-R1: the strictest license along the lineage applies. 2026-11-15
Text in
README.md
Text sha256
1efd1862e40cb7cc27cacde791d6b5ae8a1fcbd9fab89fa4c087b67ee5933d53
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-R1-4bitDate: 2026-11-15Commit: 5aa5895Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-R1-4bit
Pinned commit
5aa58959991bd42ce9c0eb634b1aff00a3410426
Manifest
DeepSeek-R1-4bit.json · .minisig
Manifest sha256
196975c13cd21c8be8894ee000796a51505640e0eb908a1b1def460ccdac3885
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/mlx-community/DeepSeek-R1-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-4bit.json.minisig $ minisign -Vm DeepSeek-R1-4bit.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-R1 · 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-R1-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-R1-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-R1-4bit

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