alt.freeweights.deepseek / DeepSeek-V4.1-Flash-1017-oQ4e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4.1-Flash-1017-oQ4e-mtp

Date: 2026-11-14Commit: 8080db6Signed: 2DC28CC7B26A283B ✓

Image text to text model with 129.1B parameters. Safetensors weights, 432 GB in all. Published by mlx-community under MIT.

129.1B params432GBDeepSeek-V4.1-Flash-1017-oQ4e-mtpsafetensorspermissive
FactsParams129.1BSize432 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
# manifest sha256 145954d9f328… · 432 GB · 90 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-oQ4e-mtp mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
From sourceHosted (signed)mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtpLast check: 2026-11-14 21:29 UTC

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

Quantized of DeepSeek-V4.1-Flash-1017.

Works with

Overview

Size
432 GB
Weights
432 GB (safetensors)
Parameters
129.1B
Formats
safetensors
Task
image text to text
License
MIT (permissive)
Files
90, each with a sha256
Publisher
mlx-community
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 21:29 UTCpassed

Model card

From the publisher at commit 8080db6. Shown as plain text with links; images open at the publisher.

DeepSeek-V4.1-Flash-1017-oQ4e-mtp#

This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385).

A mixed-precision MLX checkpoint of deepseek-ai/DeepSeek-V4.1-Flash-1017, a minor update to DeepSeek-V4.1-Flash with improved reasoning, coding, agentic and visual performance. It is a multimodal mixture-of-experts model with 552B backbone parameters, a Causal Encoder-Decoder layout, Compressed Sparse Attention 2 (CSA2), Engram conditional memory and DSpark speculative decoding. It includes the language model, the Engram tables, the vision encoder, the multimodal aligner and the DSpark MTP weights.

The effective average is 4.365 bits/weight excluding the Engram tables, or 4.529 bits/weight for the complete checkpoint.

Quantization and Bit Distribution#

oQ4e keeps the original FP4 and FP8 projection precision, which already fits the budget, and quantizes only the Engram tables.

Storage formatLogical weightsShare of totalTensor storageEffective bits/weight
MXFP4, group 32557.171B73.004%275.669 GiB4.25
MXFP8, group 325.959B0.781%5.723 GiB8.25
BF163.419B0.448%6.369 GiB16.00
FP320.042B0.006%0.158 GiB32.00
Engram affine 4-bit, group 32196.614B25.762%114.444 GiB5.00
Total763.205B100%402.363 GiB4.529

Storage Breakdown#

ComponentLogical weightsStorage
Language backbone551.881B300.132 GB / 279.520 GiB
Engram tables196.614B122.884 GB / 114.444 GiB
Vision encoder0.485B0.971 GB / 0.904 GiB
MTP head14.225B8.047 GB / 7.495 GiB
Total763.205B432.033 GB / 402.363 GiB

License#

MIT, following the source model. See LICENSE.

Files

90 files · 432 GBWeights 432 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 90 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
LICENSE1.08 KBf2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
README.md2.25 KBe92b298a5a4c612fc4a5dfcf05716b800918ad1552f1480b289ec4004d22ce59
config.json50.3 KBcf4fa70445b6f8db1e1b17fd3670ffd834fadd616b4d59d30f1ad07a970d3bd6
model-00001-of-00082.safetensors61.4 GB690072f5285b87c546f3f201a335d80e9fb9d2ebac42adb10661fc597ef75ac4
model-00002-of-00082.safetensors61.4 GB4631630246946c8e7a9137c343cef999e937b59f1542f8fcf3963ac1ca828627
model-00003-of-00082.safetensors3.58 GB95ccce04fe4e3c7cd59ce95e8791a53efe3a12800ccaeb4cf138afcc754cf3e3
model-00004-of-00082.safetensors4.99 GB05dc936eaa4b7b60cc88adec60cc46108f0f392b383bae0da69f15fe9811b0cc
model-00005-of-00082.safetensors2.62 GBb637220663ba3a7d2a804a2797bba4686c209947a553c1b9debaecb8719d21eb
model-00006-of-00082.safetensors5.00 GBb6b46818d5f42a007cd93f76f0052be7a57e0adb00a9af7fadbe47240dd42dc4
model-00007-of-00082.safetensors4.84 GB19485bab9de70c015fe7c0bf983e9c495b30bf979d8f0619aa99f821a86363a5
model-00008-of-00082.safetensors2.61 GBaa9cb66072c4cf99a034d46cf80cb669f44095dfb2d27f971c1e1c9292c17c45
model-00009-of-00082.safetensors4.81 GBb2f9272d16544716166a7a62560913a0d1b90745a3674dba67aa3b2d32b99402
model-00010-of-00082.safetensors2.61 GB69d22f7fc4f604a1bd8bd019357cd0b9dfa492fd08b3c8ac8de1759b9b73a212
model-00011-of-00082.safetensors4.81 GB681e96161a0b92b11d60142cb1a577d9e1cbf17f928850148c38e68c9efdcec5
model-00012-of-00082.safetensors3.94 GB1311f931bc6b4647e3fbf7f1e19f1f027fdad9c0922f6e0a9c77b02412765e38
model-00013-of-00082.safetensors4.81 GBff3d9289c6f3975ceb53ce414e13e0e2493c3d1b3beb2d396c59977c1ab1d5b3
model-00014-of-00082.safetensors2.61 GB8aae48efc23fd1f21a64a9fe56b9061cc00e136df765e3da996009eab265c495
model-00015-of-00082.safetensors4.81 GBe9d8614ed269dd784347a328276b3c1d33b3d2fe84d6a9c51b3f66bc28109b4b
model-00016-of-00082.safetensors2.61 GB09a0181c71d49ac38a52cfb35bb2de4856f1a1b31868247e89fd29c3969707bb
model-00017-of-00082.safetensors4.81 GB75709938154ec9c121e99582c8a011c13252774e8dd2657ddc43413cb34ee16d
model-00018-of-00082.safetensors2.61 GBae854e19b617c7ad2474db2cc75f8ca604e782099f87fa009f369e13413c096d
model-00019-of-00082.safetensors4.81 GB5e713bcc781e8a37c77f9d1e16c4cad5133107c366f3135f8efe50947ffeb0ac
model-00020-of-00082.safetensors2.61 GBae248830c4ad2b72727dac0be523514c918b7bdc023975e008bb540d876a050d
model-00021-of-00082.safetensors4.81 GBf6071340339dca731196a5bab67261927e7a9e655e7f01668f39bcf9a2573743
model-00022-of-00082.safetensors2.61 GB48b4d0fc2261adf9eb617725ec52e86b1a93b489d9031c03c48ea5195cecc565
model-00023-of-00082.safetensors4.81 GBa74aa18ee20980f20bfc065580f1836de4ea3237a768b44a4a41f53f3ee9eed8
model-00024-of-00082.safetensors2.63 GB83519f29598c5ea6865ffab56610661b74ab61ed13404ed101f743ae4c37ac55
model-00025-of-00082.safetensors4.81 GB813eaea8d1d90791b9802669b35ba5bd6fc6141b18fed24416b715a2440ad5ce
model-00026-of-00082.safetensors2.61 GB1ccb2fe74812c1d7132b7b3cb5f1445966a5a2aeb3281d02f05d32e7f4447e0b
model-00027-of-00082.safetensors4.81 GB1714a280e29fafbfd609d2f451caedc2f367efe9a4c0e1e9d56ab6eb3739c630
model-00028-of-00082.safetensors2.62 GB40456951549bdc96812055741bbecf9d0b50d0e1899a0f13acad74c8217a11c7
model-00029-of-00082.safetensors4.81 GBd0075c29d08a5ac6e5be737a3e0f1c47f4c507fa942587ac8c5d1b3051b4b063
model-00030-of-00082.safetensors2.62 GB78c0fd0c0acf9e34d017cb61bc16545db1c9982f9cb77927fc7283c45baaef3b
model-00031-of-00082.safetensors4.81 GBd876afadb67a5d5e2fc0907879750797a1e0d127a33108aecc53ae5226f8c3cc
model-00032-of-00082.safetensors4.10 GB5c83a56dc029d2f2a506f4eeb705ba21bfd68b5d51ed2a8cf204bd6c1a2d5403
model-00033-of-00082.safetensors4.81 GBea5d4d81da9995cb282d9511dd715073051722d9e20ec167c3e24b33c24b42f4
model-00034-of-00082.safetensors2.61 GB1d1d2d11d15d666ac584ccec976446b137caa409f041679e95a6af9e51966efb
model-00035-of-00082.safetensors4.81 GB917ffa738945344de9d8ab8e3cdcc8abec3db6c08fad2df39df8f48f3f35ae79
model-00036-of-00082.safetensors2.61 GBbe7b39bcdba3938ce92f795fd82642ad73054ab1851ad4a778df818d91b8925b
model-00037-of-00082.safetensors4.81 GB2b60ea5a9a351bcff5e2527376a9a13e7b04cf73e3d715c83ef0ec1d09ac05a3
model-00038-of-00082.safetensors2.61 GB1a8032a609017f64955c7864f25c1f50031e955e3922aeca90b75e84154228ce
model-00039-of-00082.safetensors4.81 GB7854c5ac450990599dd839b1cb3ed642154f7e2e6c6bcebb44d80233216b5b0b
model-00040-of-00082.safetensors2.61 GBb3a5b1de54e9512e29fa8bfc5b95748c7c7d2dcef5f8ee600b7bd226f82f7717
model-00041-of-00082.safetensors4.81 GB273061f331ce4750a1b9a0c73d7105825e6dc0c4522241a0c17e820fafb22712
model-00042-of-00082.safetensors4.22 GB84dff077c12e013a72c212910f93a8abf75e55739b1cc01134bffdb0fd14e8a7
model-00043-of-00082.safetensors3.51 GB9964a99578a077e873c37cbb5e321a4e3d509a0c37e26d3242567d87728ea6a2
model-00044-of-00082.safetensors5.00 GB09001b3fa8037aa15ac120752497ad23097d439565c9ab152f993bd8485a355c
model-00045-of-00082.safetensors4.84 GB72619874251503fd554d0d1ddf85df4120801ad865932c971aa182824cb191c1
model-00046-of-00082.safetensors2.61 GB35eaf3d3c55a695ad05516f6c7dfb97fa046de637b053748c0dffa9ff51f0a6e
model-00047-of-00082.safetensors4.81 GB07a5c63b148ae08ab31acdee97615313453a565e4305697bf9985a6a7db0786d
model-00048-of-00082.safetensors2.61 GBfe56dd067b6c4edd7063deab1782a625a82dd4dddc681d2a53d9377c144f5c43
model-00049-of-00082.safetensors4.81 GBb3e9af675a1cf3fde195871196a9b29f53f119eb922f25ee6f5debcc22dad1fe
model-00050-of-00082.safetensors2.61 GBa581d0a8d1b252d01b259b93c1a6c3f4d2611d3eb9ff7087699cb312f474b360
model-00051-of-00082.safetensors4.81 GBe76b30a4264e32195f4d9adbaa29174ea38efefd5fd12c809a0b74e6e912f547
model-00052-of-00082.safetensors4.22 GBc113fcbce0ad3942d8c71846871571cef5542c45632ba77156e4c8bf1227a915
model-00053-of-00082.safetensors3.41 GB4ced0c5401546053fa9d0213bde835da2936818e9e881d01d1c9dc6e9e56d99c
model-00054-of-00082.safetensors5.00 GBd75aaf867ee905c4c1f40d79780b96d26c680a3eee28157c7d80b7bfb6ed6762
model-00055-of-00082.safetensors4.84 GB572d72cf945bd7b92c50a02e556d37a99f9d52f3382500f36eb70d7255304a6c
model-00056-of-00082.safetensors2.61 GB383d2512a53b9809855f40cf219f9a377d106a17f7f133be02661037f7b1fddf
model-00057-of-00082.safetensors4.81 GB8cbf878c5361f9275add82773a1832c5ed506d6c3e729d669cb1fe868fb72c0e
model-00058-of-00082.safetensors2.61 GBba94f06a286e6b54707808b5c73078ef4aa4b86f243e125164b5dce300422bd5
model-00059-of-00082.safetensors4.81 GBa8cdd1a1d39312d45bd0c71122598bf04906ca44a07ad1a5064951304d8c4a75
model-00060-of-00082.safetensors2.61 GB470b5cd5e4d5b70fe43f0b190fc94e140924ec42600008ea220b6355d4867fc0
model-00061-of-00082.safetensors4.81 GBd21da1063e07252caa5348dfccb2a7af1898f2fb5966ea7f88ed867321518b69
model-00062-of-00082.safetensors4.22 GB21288b30c04411505bdb3a999ff0e54402954dbf54dd682415dac2e79e26a6f3
model-00063-of-00082.safetensors3.55 GBeb9aed44db0db2da17114996ec2557f2bff0b35ecb84e45f331f291475f655a4
model-00064-of-00082.safetensors5.00 GB8dccbbbcddd48ee3d23a387c238b55884f03bd7de911e060d0ea69e7a79485dc
model-00065-of-00082.safetensors4.84 GB27496da512542e4aa3a30fe51143509c4931fe0d6158274fb1ae40e966243b88
model-00066-of-00082.safetensors2.63 GB2db2d9419351ec7ad4db5d4f90754ea6599d6c6d06aac419c92d7f4445373725
model-00067-of-00082.safetensors4.81 GB5cd438ee4aecd7d6e32d3faa407e80e43fba6e34ead6bec2a4687495bedaca2e
model-00068-of-00082.safetensors2.62 GB3318a32b754c4cdb35c6c37a61910d1b53713869f8d1c5fdbefc4c3c313b5207
model-00069-of-00082.safetensors4.81 GBce732d9f1bed963e3652afc6d152d0d94722e7ce54bc705db0ebd22fad937c8e
model-00070-of-00082.safetensors2.62 GBde755d46b152b783aefb58e7803e6d274d50d5bfe4629d02dfb8c506b832ce92
model-00071-of-00082.safetensors4.81 GBa71ff2281b82d365b133d067aa848bd49c24e421c60a545784b22aae71d06729
model-00072-of-00082.safetensors2.61 GB336187ee3b0a1dd6849b41a9496a3b7df3ab5ad36a072367a37269ea98378b0a
model-00073-of-00082.safetensors4.81 GB14075887b098c791486de96f5c1c1e3e3a81cc3711ceeb591e07ba81cf0f2008
model-00074-of-00082.safetensors2.61 GB72ba535cb8630d6663e39326d21206ceebf2127dd5a6de619fbe9ecbdeeeb7fa
model-00075-of-00082.safetensors4.81 GB14690873619b069300e7ae01398a910216e2ba334e2514e6d7d7ea3bae93d9c7
model-00076-of-00082.safetensors2.61 GB10564590ad76c2c27391a66b6f5040661594f260eacb88af9a20d31881c787f0
model-00077-of-00082.safetensors4.81 GB99f4513fc2ce36d120370c6e1e0e7d743cada87cb600799d8dfa224cc28ad9e4
model-00078-of-00082.safetensors2.61 GB92191861b058cbc3a7a2c88325d8c26028242d1b8a93f3c83d0115260f48d71d
model-00079-of-00082.safetensors4.81 GBc6aaa945e1cf962bdfdf0d7c5e05ee038a925e2ac2ced11040fafced3f1b6f38
model-00080-of-00082.safetensors2.61 GBc780dc36959718766484c09e75da0f6d77fb5723ab0b23c3c673f7afc0e3dcea
model-00081-of-00082.safetensors4.81 GB2e298f5addf9c6501341fdf8c6afaf9556b9a3927654604fd73a075e05999f0b
model-00082-of-00082.safetensors2.41 GB0aa49794e1fbaee0a3868e26dc7f8b3f459871a1bee76edf2ec34cc32cb2f925
model.safetensors.index.json156 KBf21412c2940e949a78cae8edc2eac6c34dd715b2570aae069fc56a382ed25988
quantization_report.json775 Bb0374399fbceade629f99ce2d55b7c87b25b515da916c533a2fcb32afb15df76
tokenizer.json6.37 MBc90dfa01249db1be4245780a052ede752e1361c612ac6d08e2bdada7d599476b
tokenizer_config.json801 B6ac8c8dc065ed118161d02dd532749ae3f52c243deac27872134fae2f50d8547
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8080db68c4 pinned now manifest updated, same commit2026-11-14 21:29 UTC90 files · 432 GB
8080db68c42026-11-14 21:29 UTC90 files · 432 GB

Use it

$ fw get mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
# manifest sha256 145954d9f328… · 432 GB · 90 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-oQ4e-mtp mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
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-V4.1-Flash-1017-oQ4e-mtp.json --dir ./DeepSeek-V4.1-Flash-1017-oQ4e-mtp $ python3 fw.py verify ./DeepSeek-V4.1-Flash-1017-oQ4e-mtp ./mlx-community__DeepSeek-V4.1-Flash-1017-oQ4e-mtp.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp --revision 8080db68c4d9323ad69e0e8c2496b0d673a336bc --local-dir ./DeepSeek-V4.1-Flash-1017-oQ4e-mtp
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp", revision="8080db68c4d9323ad69e0e8c2496b0d673a336bc") model = AutoModelForImageTextToText.from_pretrained("mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp", revision="8080db68c4d9323ad69e0e8c2496b0d673a336bc", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp --revision 8080db68c4d9323ad69e0e8c2496b0d673a336bc

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
LICENSE
Text sha256
f2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
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-V4.1-Flash-1017-oQ4e-mtpDate: 2026-11-14Commit: 8080db6Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
Pinned commit
8080db68c4d9323ad69e0e8c2496b0d673a336bc
Manifest
DeepSeek-V4.1-Flash-1017-oQ4e-mtp.json · .minisig
Manifest sha256
145954d9f32843cdf56d0e5a3583b318e92a670e65f8b95aaf1f72778e133279
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:29 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp.json.minisig $ minisign -Vm DeepSeek-V4.1-Flash-1017-oQ4e-mtp.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 mlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp
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-oQ4e-mtp.json. Provenance. Takedown history: none.
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