CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-R1-3bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-R1-3bit

Date: 2026-11-15Commit: 4c0731bSigned: 2DC28CC7B26A283B ✓

Model with 671B parameters. Safetensors weights, 336 GB in all. Published by mlx-community under MIT.

671B params336GBDeepSeek-R1-3bitsafetensorspermissive
FactsParams671BSize336 GBFormatssafetensorsTasknot taggedLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-R1-3bit
# manifest sha256 fe28e7dcd551… · 336 GB · 77 files
$ fw verify ./DeepSeek-R1-3bit mlx-community/DeepSeek-R1-3bit
From sourceHosted (signed)mlx-community/DeepSeek-R1-3bitLast check: 2026-11-15 05:12 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
336 GB
Weights
336 GB (safetensors)
Parameters
671B
Formats
safetensors
Task
not tagged
License
MIT (permissive)
Files
77, 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 05:12 UTCpassed

Model card

From the publisher at commit 4c0731b. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-R1-3bit#

The Model mlx-community/DeepSeek-R1-3bit 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-R1-3bit")

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

77 files · 336 GBWeights 336 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 77 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md761 B8db0450b5db63894113fa1e743dc21c1d39370a2220a74c183876be5238a45b0
config.json1.85 KB21140a398449270d07f3de86e5d03bbb263cb68bf300efe127e460d063ee54fd
model-00001-of-00070.safetensors5.19 GBfdbf59fe5206b7e9d9f8fdfc675a1b167fdd7c4106254f6475f7f336e7e14ce6
model-00002-of-00070.safetensors5.29 GB465650dfc1c377b7a1ec19172f6126cdee15a03478928b87d2deeed739edc1be
model-00003-of-00070.safetensors4.35 GB914974aa50437b8cd482517dfad72c1795c34f9dab6374f58997ea042b67d6c9
model-00004-of-00070.safetensors5.29 GB0a55ae58e1faa43fb40d747046a9bdd65d8629cf20e2c28ce57e27a490d753aa
model-00005-of-00070.safetensors4.35 GBaa5981a4920198bc8590aebbf479d9e1c08d895b50c6af39fc18c9829b5ba370
model-00006-of-00070.safetensors5.17 GB5fdfd53c684c61e24b84e510debb7e98259232fd5157e07ea65ba0ef2529825f
model-00007-of-00070.safetensors4.35 GB5b7891bbc343b74d1b46f48ea6d6dcfb72efe21cdaa33f397fb298de2b473e6e
model-00008-of-00070.safetensors5.29 GB5ab274ffc532ac7ffe100ee7a3593f9d4e1a2e1edb0d87b944381c57b55fe947
model-00009-of-00070.safetensors4.35 GB74b529093d9182ef3691a987f536cc1634172afe1ca62f466e024cf153b9e1ad
model-00010-of-00070.safetensors5.29 GB6ac831496b0745ad54f38299a6babca0fe81d21763dab1794dc70d6490181c39
model-00011-of-00070.safetensors4.35 GBb3814ed7047bc9e75e7fb153bdf667ffd64d5eb38328f38c5183b4278117cd34
model-00012-of-00070.safetensors5.17 GBf62bd81a5bc4488ecfa5004ba387a0f6e8c2f4950e7cf946272067526ce59a11
model-00013-of-00070.safetensors4.35 GBb89426287a8ed085c370729ab6f6dd17d9957aeb9000af05b5c0e1ecb18f3b48
model-00014-of-00070.safetensors5.29 GB0799dcc38454e9a4976bb728d77e86c58c3bafbcf29e84f28fe6e9b997078eb5
model-00015-of-00070.safetensors4.35 GBdaabc8afaf3096adfedd30454fcfc58ed5fef1a5e9c47a0f0fcc29c5f5776e23
model-00016-of-00070.safetensors5.29 GB91ddc966f98bf32b80840a06f3e5efbccc2cc971568eb03de7213554bcbeeff8
model-00017-of-00070.safetensors4.35 GB829f4ece499a65e66000190e68a0e4e95e958640f538ed7581bfe8736f7b476b
model-00018-of-00070.safetensors5.17 GB4805117d67eaa00eb07fc7b558947b8e80d87d11fbfb50834525ca4bd1c88990
model-00019-of-00070.safetensors4.35 GBda66c48a19e1c7cb8e1f2b62c46a409d24194a101f47c8046fb1a53084175a22
model-00020-of-00070.safetensors5.29 GB9bbd2b12f06187f4e4c91274351cb956ea28f5edc293a5b689b13fbb71727a4f
model-00021-of-00070.safetensors4.35 GB78a4890a3954c9b9a629d01536994eba10a707b7b95dde4435f496d063c44526
model-00022-of-00070.safetensors5.29 GB5ca4d366e4d8a262b66c6a1657a403b8814cbe138b61c6c25852aae175f5e912
model-00023-of-00070.safetensors4.35 GB35857c082ce32e171db9a5e4d7b7bfc89806792d69e9d2f10ced9f0a02876c51
model-00024-of-00070.safetensors5.17 GBe84afb71461fd743778da3895431a73a7dd5401292bb06c6c5ca78e41250f3f7
model-00025-of-00070.safetensors4.35 GB780f1a7f9bdaf05d0b8219326051842c84bbd8cf5bafd4d070c413dd0385b7d9
model-00026-of-00070.safetensors5.29 GBf6f23be93609b8bce9e74df36b1a1fe8efd7b7ba3d0645419198dc668e5126fb
model-00027-of-00070.safetensors4.35 GB37e0e7f9d9991ba431568822bdf554f171f3221b37cd3c8536e44041afdf98ec
model-00028-of-00070.safetensors5.29 GB0f5fd7bbd7582c529045cbdfa883e2c0f528c1861216c8b58ac0236fe2a20351
model-00029-of-00070.safetensors4.35 GBd8a138177a425430bedbc507caba9cda5b19affde8cd5bce1a8b8fa73f980435
model-00030-of-00070.safetensors5.17 GBb62e8ee05bc012fd06f1624208cd4ee6e9a917a1a8983ddc2f7436f184e8a7d3
model-00031-of-00070.safetensors4.35 GB01564e1183163276a9c7f18f24c6432f99da140740f213d57214b487af9b2ad3
model-00032-of-00070.safetensors5.29 GB49c1a99b26047598d40998094c723a33b72d04e75d35e3f2504ca5548f8a354b
model-00033-of-00070.safetensors4.35 GB0ba7ea2f4298834c63a7a0a4ff4be8e017f82d159ac469dc720ff546962ca564
model-00034-of-00070.safetensors5.29 GB65f5f427e8e7a7c43818b907ca2ed8bb2c0b277f5d10fc26055e542d3e4755a9
model-00035-of-00070.safetensors4.35 GB71f2960b68835662ec6013baf8cca4018ce5c6e90e9fbe08518eb233d096bdd9
model-00036-of-00070.safetensors5.17 GB6e97cd020533b75a6194fdba94af631f4bfe87b9f8975a0283a3eff7040aa338
model-00037-of-00070.safetensors4.35 GB719c9d91c0a988331e01b203bcbd689580a3b64cf4077c9cee6fc8fa982f4782
model-00038-of-00070.safetensors5.29 GB898fc23e751da7d57e08b9ef5e643c15b410eaa4968edd33efb70d0d17281d81
model-00039-of-00070.safetensors4.35 GB9a5d7f726ae28a1de7c7866d33333602422a66b48537ebf2e5fdabaf24c99230
model-00040-of-00070.safetensors5.29 GB5c0d9a7dee43a88071cca8c3008bd7cc1523c3f4ff71fe34e77522b7d0259f9b
model-00041-of-00070.safetensors4.35 GBa123d07789c54ff6274b8dac615e542d7500f83d33651c8af69004abb9bb3f17
model-00042-of-00070.safetensors5.17 GBcec126a5ce754dd526d1e43f29f8ffce1047969298fec73035aea630b7a25927
model-00043-of-00070.safetensors4.35 GBefebbb62131479edb1a1d3f23ab2a6bb7a92961f8ad340e8dffa5636d4efe859
model-00044-of-00070.safetensors5.29 GBc533f1d7262c8fa049c48deba329a662c0ca537c3d12acb01e1dcaf8e9b27410
model-00045-of-00070.safetensors4.35 GBac813fd8c8fe37b91afde5aeddcfd41a30626ebf8633785581ffdc11928fb53c
model-00046-of-00070.safetensors5.29 GB5ed529eabff86dd71a282f3d1e9799b8b5d7bd0af5436e763d5d3fb8ed913408
model-00047-of-00070.safetensors4.35 GBf3e0b9cce4b9b990f144039471be4cb5296110e43db5e2a5f90cd9dd6cae3fab
model-00048-of-00070.safetensors5.17 GBfc9effcb48a63447505602b51340b3b968b844be1ec23d79333adb0ef13dd94f
model-00049-of-00070.safetensors4.35 GBa4aef8f0a40eac810004142cb2f2b7e914c6b6d08ec3c498c1df258d9f3f6789
model-00050-of-00070.safetensors5.29 GB6700a818b93d0a1c0a8eed7b031dae66e271852c82b3a65ae8f185f8d335e12d
model-00051-of-00070.safetensors4.35 GB6a732184cf0c1d4b73ee0bd84d33da567f558a86180f6bda2ed65dcbb947d293
model-00052-of-00070.safetensors5.29 GB5b4343babdcc06da77c2e71a65759dc20d2c144fdcaafdeae7068fa5ac468ea2
model-00053-of-00070.safetensors4.35 GBc694810c0e75cec78161b03dcb85e326af4978c8e712d38b9e172e8eb43440e3
model-00054-of-00070.safetensors5.17 GBc106ca82fd9394d28f14980b7ff5f6db81951ea12138018664ea2dc8c5b6fb1d
model-00055-of-00070.safetensors4.35 GB626b519df6e16151f35d3f5de2f384d0d2a7fc73f6414e03de774e2f4d2e7baa
model-00056-of-00070.safetensors5.29 GB05fe4bb0092c00e301f579014080c1aa2f0ab7ed00fbbe04b007c17984f1aa2c
model-00057-of-00070.safetensors4.35 GBc76431264d172558c9ae3081ba8a3fcf571d8ff56f8dc765d581d285ec8d65f6
model-00058-of-00070.safetensors5.29 GB8fe5dac48c500b36e70c521f89b19aaa7be7545531696b3e0a93bb563d4e55d2
model-00059-of-00070.safetensors4.35 GBbc131bb757437339dd496661b700d7d0986a3d1c9df19267ad34beb29b2498f4
model-00060-of-00070.safetensors5.17 GBabcb81bd6636b2214be480005222c6044fe70bfd13e8369f0894692a1b6c6eff
model-00061-of-00070.safetensors4.35 GBfa0f93c13b64a3d775f6fff67d8d4ad8ae0994816ba593c6501d7108c12b427d
model-00062-of-00070.safetensors5.29 GB154bbc36a5ee9ff8fc07656976b3741f4e429ef4e6e07b5980d8f10196edb146
model-00063-of-00070.safetensors4.35 GBae80f14613443b4aa31f6413a188bb871b54c5a93f3b2899cacd7cdc945481b5
model-00064-of-00070.safetensors5.29 GB89be87915165c2f1ced807d49c88ebe105d7b92f967660792d3a7db9273556c9
model-00065-of-00070.safetensors4.35 GBb98353aa9b3c67aaaa8e22f559da5fd45d4571719c360f3a36872f8bf137bf84
model-00066-of-00070.safetensors5.17 GB005d03c9150a0dc8fb5ac30747ba7e3fb647a836a88f56e33560bfb05e727f32
model-00067-of-00070.safetensors4.35 GBbede92653610a1312f15bfe8431c385c64c642470f9e6850a0da4e2258139055
model-00068-of-00070.safetensors5.29 GB8ced928510690e76b4062f66bc30e1f0456a132f37ab12c5a7eaa6f8ed9461ee
model-00069-of-00070.safetensors4.35 GB07c5ea9419b486f053665760c39f0cec7ef8fc7782072700c2e9d58dd0ee04c0
model-00070-of-00070.safetensors4.25 GB6c8bce3d8ecb5ea86aee6daf0dc0ea53a9ed0fc6d71e736c621a55b67d27aa19
model.safetensors.index.json219 KBc381658d961907e17cb036982fc8d96f5e4359f9987df33d258fa52139fbe6f0
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
4c0731bd49 pinned now2026-11-15 05:12 UTC77 files · 336 GB

Use it

$ fw get mlx-community/DeepSeek-R1-3bit
# manifest sha256 fe28e7dcd551… · 336 GB · 77 files
$ fw verify ./DeepSeek-R1-3bit mlx-community/DeepSeek-R1-3bit
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-R1-3bit.json --dir ./DeepSeek-R1-3bit $ python3 fw.py verify ./DeepSeek-R1-3bit ./mlx-community__DeepSeek-R1-3bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-3bit --revision 4c0731bd49ff0a1ee87425982ebcdc5be2ecc0b6 --local-dir ./DeepSeek-R1-3bit

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
8db0450b5db63894113fa1e743dc21c1d39370a2220a74c183876be5238a45b0
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-R1-3bitDate: 2026-11-15Commit: 4c0731bSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-R1-3bit
Pinned commit
4c0731bd49ff0a1ee87425982ebcdc5be2ecc0b6
Manifest
DeepSeek-R1-3bit.json · .minisig
Manifest sha256
fe28e7dcd5519a01179093ed7761aaf2b92c141af54681a05bf5d1074eef010b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:12 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-3bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-3bit.json.minisig $ minisign -Vm DeepSeek-R1-3bit.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-R1-3bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-R1-3bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-R1-3bit

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