CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp

Date: 2026-11-15Commit: 7845611Signed: 2DC28CC7B26A283B ✓

Image text to text model with 102.4B parameters. Safetensors weights, 343 GB in all. Published by mlx-community under MIT.

102.4B params343GBDeepSeek-V4.1-Flash-1017-oQ2.5e-mtpsafetensorspermissive
FactsParams102.4BSize343 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp
# manifest sha256 cd34621196e2… · 343 GB · 61 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp
From sourceHosted (signed)mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtpLast check: 2026-11-15 04:54 UTC
Get help

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

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

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
343 GB
Weights
343 GB (safetensors)
Parameters
102.4B
Formats
safetensors
Task
image text to text
License
MIT (permissive)
Files
61, 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-V4.1-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.co2026-11-15 04:54 UTCpassed

Model card

From the publisher at commit 7845611. Shown as plain text with links; images open at the publisher.

DeepSeek-V4.1-Flash-1017-oQ2.5e-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 3.104 bits/weight excluding the Engram tables, or 3.592 bits/weight for the complete checkpoint.

Quantization and Bit Distribution#

oQ2.5e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (1024 samples x 512 tokens) and a weighted least-squares refit of its scale and bias. Below oQ4, the Engram tables stay at 4 bits and are left out of the bit budget, because oMLX can serve them from SSD instead of memory.

Storage formatLogical weightsShare of totalTensor storageEffective bits/weight
Affine 2-bit, group 64308.030B40.360%89.648 GiB2.50
Affine 3-bit, group 64235.552B30.864%95.977 GiB3.50
MXFP4, group 3213.590B1.781%6.724 GiB4.25
Affine 8-bit, group 645.200B0.681%5.145 GiB8.50
MXFP8, group 320.779B0.102%0.748 GiB8.25
BF163.399B0.445%6.332 GiB16.00
FP320.042B0.006%0.158 GiB32.00
Engram affine 4-bit, group 32196.614B25.762%114.444 GiB5.00
Total763.205B100%319.176 GiB3.592

Storage Breakdown#

ComponentLogical weightsStorage
Language backbone551.881B210.811 GB / 196.333 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
Total763.205B342.712 GB / 319.176 GiB

License#

MIT, following the source model. See LICENSE.

Files

61 files · 343 GBWeights 343 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 61 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
LICENSE1.08 KBf2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
README.md2.65 KB27f581b561f85374fc46f89dcaa160f2d39b93154bc0dce869fc8b821a51c2d5
config.json134 KB74259bebe816bb248eb075a9c285c64eb705d9ced63777ef5b0a9263b06793c6
model-00001-of-00053.safetensors61.4 GB690072f5285b87c546f3f201a335d80e9fb9d2ebac42adb10661fc597ef75ac4
model-00002-of-00053.safetensors61.4 GB4631630246946c8e7a9137c343cef999e937b59f1542f8fcf3963ac1ca828627
model-00003-of-00053.safetensors4.01 GBe65f647085e2b5ec750efca6968e38a3c91ab3a1e372b258394fc60b4de999d5
model-00004-of-00053.safetensors4.35 GB17482bd34bcd322f4f3a0b08d0c51c8ef4acb709833524e7ec3d0ae533ff34d8
model-00005-of-00053.safetensors4.18 GB2f61f330080c169a57937f713de1bab4e4bd99a8976e4e918e495b1129dd36da
model-00006-of-00053.safetensors5.00 GB0d14ad3a3fc82c04b20fb797a23a7378308004d63f9303ed2c21a9d30495fb4c
model-00007-of-00053.safetensors4.97 GBd2f0c25c83224643b498cd3b6f8ac2234939479cda11bbae93c031dc96bdbbb0
model-00008-of-00053.safetensors4.90 GB5c33bfe5fffcaea55efd2a04124f7a0d5cd9ee853c668e53805b372f39cc3e56
model-00009-of-00053.safetensors4.36 GB895c4be427ada59bd331086fa7021bb99f0bef7485e98a6687b2d89889b2ae42
model-00010-of-00053.safetensors4.18 GBd684cc9845e1e646aa0d2c2a098f7f3bcf6b416469bdc6cadd9228ff1cff7107
model-00011-of-00053.safetensors4.18 GB7762a1cc5a7f20a9ccb131cebb1dc7aa39442f4037207b4d37845f0b9053ac4d
model-00012-of-00053.safetensors5.00 GB00c34b2395faa5887b7fffc4d7c10e4edc3f9415930948596fbc6aa51cf1417c
model-00013-of-00053.safetensors4.97 GBa77400eac6a268ccb576fd75cd1c4861f18ca58e573a2f5b31853b847d578fe7
model-00014-of-00053.safetensors4.05 GBf3e83acd99d935f646468bc7f377fd266c14e1b4ef46b512a2430c9b6992cd8a
model-00015-of-00053.safetensors3.61 GB4ebef9afe16d3a0e3324d71016a663c5b8665c2b7b0e6d979dcdad8f5bb175b8
model-00016-of-00053.safetensors3.62 GB6a9d001e14a13a5b99da3ebc61c9dbf7c37d149b9cd6b7e569b6edb8b3c67dae
model-00017-of-00053.safetensors5.00 GBd10a9f011e23b598d38a8896b5195ca8bdcbd5609b410a514ef1e89202e79100
model-00018-of-00053.safetensors3.99 GB018947debdd66d3fd519dbfd8df5b4c5babac3972744773b25ab41b249b49caf
model-00019-of-00053.safetensors3.61 GB9991cbdaeaac671065f814b9c6625f79046ae8aff6d44969d84e0a5843c98621
model-00020-of-00053.safetensors3.61 GB8324a9b2c6057b7827c4b3824995a436de68f6930f02bff2ed684f522786a5ae
model-00021-of-00053.safetensors4.82 GB7d290a6f52f6669c38d59efbe1acd838d1493696edc691b7e75e8e87dfe38844
model-00022-of-00053.safetensors4.52 GB283414e9d1204d2bca0cdb5488e161ca27f31b13433761e1a6b063d48f1e5274
model-00023-of-00053.safetensors3.61 GB64486463ea1ffd222ba2c9d35be2e0cb7709fc7e5c5322e95a2d0a7843493c68
model-00024-of-00053.safetensors3.61 GB8a2869db21b8001cd81e0e5dea7a945acaa9275c2fc831d852f7505d9da35419
model-00025-of-00053.safetensors3.96 GB4dbb196370d04ce2af739d84c85c883b855c03fe8d5b94e5a4b32e39cecd620d
model-00026-of-00053.safetensors3.61 GB6a2af4126a70f21fa62bafa24508aed00bb17ddc833fb8b510fd3a718bdcdeb2
model-00027-of-00053.safetensors3.61 GB70bb62ac9b6484546d6eedd1cb66fa30baa2373a68ffe17fd752d34628d593ee
model-00028-of-00053.safetensors5.00 GB54448da3dc87ec7a2290c84895f2919e8f1a8c09592866f69ad087915608c89d
model-00029-of-00053.safetensors4.15 GB505e26d961fe8b7f495838d017ddcd284f4ff08964010c26dc059d7b121df65f
model-00030-of-00053.safetensors3.61 GB8c4102ab91fc33d45cfadcc070c574892c7200de2093506f57d1e574ef684db5
model-00031-of-00053.safetensors5.00 GB8880ce8dd0177047cb5567aa87eb59826e82c9200021b1626264ecd659c9da64
model-00032-of-00053.safetensors3.99 GB9c391613f32ab2cf0eb84f6333b40c34bc80fdbfad5e21fb74a8846e97a47dde
model-00033-of-00053.safetensors3.61 GBd7f369b96704ea26d4c30d1c59978f3cb6dfa6ebeedbd002c505785f53e6af48
model-00034-of-00053.safetensors3.61 GB53952fad0c4438ca83244e0e0e2386b989ef479b1c0513eebfd62d7843d1eef4
model-00035-of-00053.safetensors5.00 GBbb8029fd0bebf78d40df4394426ff9c4a4645accee35880aaf22997f67086b8f
model-00036-of-00053.safetensors4.06 GBe99920e790020d9040e70013499f369b9632910205ff45c9ab0b088746c4d8e6
model-00037-of-00053.safetensors3.61 GBac5304bf189cc5f9823944e5446724af45d02823b63d5728085e58874bc0a9c2
model-00038-of-00053.safetensors5.00 GB2f977b56a603c35237fd5ed8e1c275f73f5a669332159898c62b04765f950c64
model-00039-of-00053.safetensors4.97 GBc0cd705b2b9fca0708b8843d5ebad5967cca87c8eb2a10008641f9a6d4472e2e
model-00040-of-00053.safetensors4.95 GB3ce88605d2ff2c820c06a72f7c44602919259c21410ea1ba711233c5f01118a2
model-00041-of-00053.safetensors4.98 GB54d281c86a354ca67eba7daeee276052170295e207057b7b196cabf1a2de88e1
model-00042-of-00053.safetensors4.36 GBa08daf93926698ffb1483c9ef49887a09535b2a9bf9a941dcade0d1ae1222efb
model-00043-of-00053.safetensors3.61 GB8556e8837d03da94080e6127750a747af10b9855b4bd4d1417703bd57e2bc26b
model-00044-of-00053.safetensors5.00 GBffda3e4c9b0d664a346abcda6b61a90fc2630c89c74a80d1e5f4675fee8511b9
model-00045-of-00053.safetensors4.99 GB024967c9c223b93b517f23cef4c287893f3a30138aa2f42908a077e83299c9aa
model-00046-of-00053.safetensors4.95 GBca6b389468d18f58957155f5e91a6bd33e378b30e92b323bec7ee2248911b09d
model-00047-of-00053.safetensors4.99 GBe993d833a030a26dbf946cda2e0acf88c9fe8340499a20f6fb712314d14184d4
model-00048-of-00053.safetensors3.03 GB219c41ffbc8a21f2e9e817075d20d7c03406c9db4fb5db665cb2a07b27e9330a
model-00049-of-00053.safetensors3.61 GB356bfd033a08f1d6ed75b7aeb00d4fdd4f65122bbd3b42e8bb0844f60bcfc9a7
model-00050-of-00053.safetensors3.61 GBf038dbfe17f8321f3c10247dabcd9e45e292c39b9c2d2e7348057e4d59725614
model-00051-of-00053.safetensors5.00 GBecb9b3964dbf0c5002f5418e5fc579159782704b7243f7babf57fa3fff339c51
model-00052-of-00053.safetensors4.97 GB1139d0387ba0dae8112d8ddce96b4a09a83b3795394c43dd67d008aa2910a577
model-00053-of-00053.safetensors4.90 GB0bfedd19c93893b13d8c676b998f2208b49540557c5845f6f625bc69437065c2
model.safetensors.index.json196 KBcf5d05c50ce04258ece0b1d47f9abb9f8ff0eeb62665088042b3088a866714d0
quantization_report.json53.4 KBafaffd6a6136b30a01f1385598d7a4508dd797f48cff7cac658222ba923250c6
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
78456115d3 pinned now2026-11-15 04:54 UTC61 files · 343 GB

Use it

$ fw get mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp
# manifest sha256 cd34621196e2… · 343 GB · 61 files
$ fw verify ./DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-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-oQ2.5e-mtp.json --dir ./DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp $ python3 fw.py verify ./DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp ./mlx-community__DeepSeek-V4.1-Flash-1017-oQ2.5e-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-oQ2.5e-mtp --revision 78456115d301eecf9fadcdcc81c0cf6f8b2c8eab --local-dir ./DeepSeek-V4.1-Flash-1017-oQ2.5e-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-oQ2.5e-mtp", revision="78456115d301eecf9fadcdcc81c0cf6f8b2c8eab") model = AutoModelForImageTextToText.from_pretrained("mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp", revision="78456115d301eecf9fadcdcc81c0cf6f8b2c8eab", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp --revision 78456115d301eecf9fadcdcc81c0cf6f8b2c8eab

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
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-oQ2.5e-mtpDate: 2026-11-15Commit: 7845611Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp
Pinned commit
78456115d301eecf9fadcdcc81c0cf6f8b2c8eab
Manifest
DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp.json · .minisig
Manifest sha256
cd34621196e23c411896dc850aee40248b30dac38e54a56e855531078f73e2ca
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:54 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-oQ2.5e-mtp.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp.json.minisig $ minisign -Vm DeepSeek-V4.1-Flash-1017-oQ2.5e-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-oQ2.5e-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-oQ2.5e-mtp.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp

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