alt.freeweights.deepseek / DeepSeek-V4.1-Flash-1017

From:

deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V4.1-Flash-1017

Date: 2026-11-14Commit: 08c8657Signed: 2DC28CC7B26A283B ✓

Image text to text model with 763.2B parameters. Safetensors weights, 510 GB in all. Published by deepseek-ai under MIT.

763.2B params

510GBDeepSeek-V4.1-Flash-1017safetensorspermissive

FactsParams763.2BSize510 GBFormatssafetensorsTaskimage text to textLicenseMITFrom sourcepermissive

$ fw get deepseek-ai/DeepSeek-V4.1-Flash-1017
# manifest sha256 90ed8b9a634d… · 510 GB · 84 files
$ fw verify ./DeepSeek-V4.1-Flash-1017 deepseek-ai/DeepSeek-V4.1-Flash-1017

From sourceHosted (signed)deepseek-ai/DeepSeek-V4.1-Flash-1017Last check: 2026-11-14 06:27 UTC

Run at home Get help

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

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

Runs with

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

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 510 GB
Weights: 510 GB (safetensors)
Parameters: 763.2B
Formats: safetensors
Task: image text to text
License: MIT (permissive)
Files: 84, each with a sha256
Publisher: deepseek-ai
Added: 2026-11-14
Section: alt.freeweights.deepseek

Lineage

Original release from the publisher.

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-14 06:27 UTC	passed

Model card

From the publisher at commit 08c8657. Shown as plain text with links; images open at the publisher.

DeepSeek-V4.1-Flash-1017#

Image: DeepSeek-V4.1

Homepage Chat

Hugging Face Twitter Follow

License

Technical Report 👁️

Introduction#

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.

Benchmark	DS-V4.1-Flash-1017	DS-V4.1-Flash	K3	GLM-5.3	GPT-5.6 Sol	Opus 5
HLE w/o tools	42.6 (44.0†)	36.8 (39.1†)	43.5	42.0†	44.5	56.3
Terminal-Bench 4.0	42.3	31.2	12.6	37.9	39.9	51.8
DeepSWE v1.1	77.0	74.2	67.5	66.9	73.0	74.0
ProgramBench	29.1	20.3	17.5	19.0	23.0	37.0
NL2Repo-Bench	68.2	65.4	58.0	58.0	56.8	75.3
Automation-Bench v1.0.6	60.5	54.8	46.7	48.8	45.8	50.3
Agents’ Last Exam	35.4	31.8	27.6	28.5	26.7	28.6
Apex Bench v1.1	72.1	64.6	47.8	56.6	54.3	65.8
Chartography (w/tools)	83.0	78.9	68.1	—	79.9	84.0
BabyVision (w/tools)	92.5	89.6	85.7	—	88.9	94.1
ZeroBench-main (w/tools)	51.0	49.0	41.0	—	53.0	52.0

† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.

Prompt Encoding#

This release does not include a Jinja-format chat template. The encoding folder contains a self-contained Python reference implementation (encoding.py) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.

For production use, we additionally release deepseek-recipe, a set of Rust libraries with Python bindings that provides the same prompt format as a maintained, protocol-aware toolkit. It converts Messages, Chat Completions, and Responses API requests into the Conversation format, encodes them into DeepSeek V4 and V4.1 prompts or token IDs, and parses model output back into complete or streamed responses — covering thinking, tool calls, images, and generation settings. Model inference, tool execution, and HTTP transport are left to the caller.

Minimal Inference#

Please refer to the inference folder for instructions on weight conversion and running inference locally.

Recommended sampling parameters:

Parameter	Value
`temperature`	1.0
`top_p`	1.0
`context_window`	1M tokens
`max_tokens`	≥ 256K

License#

This repository and the model weights are licensed under the MIT License.

Citation#

@misc{deepseekai2026deepseekv41flash,
      title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression},
      author={DeepSeek-AI},
      year={2026},
}

Contact#

If you have any questions, please raise an issue or contact us at service@deepseek.com.

Files

84 files · 510 GBWeights 510 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 84 files with their sha256

File	Size	sha256
.gitattributes	1.59 KB	ed873bb9e14080be645f511c16c90a303e6112d92f8a8b50d6bbc60eeae45453
LICENSE	1.08 KB	f2c6c602815669d292889e5be8c802f2ed950653b77999b1584e8e6aed25d040
README.md	5.23 KB	b72b796e4f4c739eca5d0ad360a7679b39118ca7eb64891f7151a527b292c42a
chat_template.jinja	16.7 KB	95b7033a693b321ceaefb6f89ad07d1e0cf2b095305711f934a4ac649456739d
config.json	3.31 KB	8be45ce0476004a3f529fd896115a4a2e800a129ad2d3ec05b16050f52e21879
encoding/README.md	12.2 KB	a34a5ca98c65e5b5b2bedd693cc2e18e732fe50192723fb6937ae07219c23739
encoding/encoding.py	38.0 KB	13231c592e958fb39e2af6001dae69d90e7a36b265702b9b390236fb387599e2
encoding/test_encoding.py	22.4 KB	288b79c9ea7d018ae03b0dd3e54a8220cc3a2df1ff97f59907e75ed8112765d6
encoding/tests/test_input_1.json	2.76 KB	6a5a86694e47169c8f0c9243a7e24cc5db05447be0d3d3a9891034e913c518de
encoding/tests/test_input_2.json	527 B	fd985cda88e8640b8e2404d8e659f7006cad204eb41f73c9e6662b1f218c01aa
encoding/tests/test_input_3.json	2.55 KB	4207613f15c79b95ad92074bdb8b2b81c5ce9cfdf15b7a67f58ded6bb3ec4fa5
encoding/tests/test_input_4.json	712 B	4c3890a7bc042ec6396d98d024a39a73cdcffbe1d0253e852da0c35e65296f3e
encoding/tests/test_input_5.json	1.14 KB	88289b0aac8d650aa55c4ffeb392818fff3a0ac83c2293ddfd90546804d5e5c4
encoding/tests/test_output_1.txt	2.48 KB	91f79aa955717b414a82aabfb38bcd83ab5a998bd47db89d2a26338e8d3de550
encoding/tests/test_output_2.txt	294 B	9fa162587b73ab9b315be5c88d433f9e0e681b4b36926952f289099ed9bc1dab
encoding/tests/test_output_3.txt	2.48 KB	cf2b801d0738c88abb691bf4a096000c0e0737faab8a54a4ba5243c5513a3711
encoding/tests/test_output_4.txt	574 B	94433b68370dcc69fa61efc5011b5d0e28685e4716fee1ee77fbbfc0c9935b54
encoding/tests/test_output_5.txt	408 B	4d673091746553d1cb2e40a3fc01dc09a7c53c40627096a3e49c97a269a81f64
inference/README.md	2.03 KB	2834402823199ee24e9a42bdf36a0fc6daf94448f444cb062c042a057a798f1c
inference/config.json	1.98 KB	2e84f45cf1dac8c7fcbb200e96667d4b913275690668ed496f24c7747207a809
inference/convert.py	9.46 KB	035028340479145594a81d6084a8424e57363adf83c0d5983914783d95614d76
inference/engram.py	8.14 KB	11f35ecbead8150c35aa002b3d180ef290b05a25afe883a11884f94d476d3897
inference/examples/example.txt	332 B	8456a2f1d5a15b7aa1f697567e34f79af0522fb694df7ac789dae9853fff165d
inference/examples/example_harmony.json	2.16 KB	44ae84a3cbd360b1b8d303ed4006756afb77e5d014c4abb7c61ff9b9a094f6ea
inference/examples/images/carrots.jpeg	212 KB	5df896a4a07e127281c60fc957f8b3d73f4735b3258a0bf762b4383557f8fa9a
inference/examples/images/corn.jpeg	56.1 KB	251fe7ad58f44db139a6af5ed489e027eca93ae60878b83f3e709c7d6f0112a1
inference/generate.py	8.72 KB	8668d67f7d108e32b90d50cb0d8606889ceb2219bfe95741d84e22f70768e9f0
inference/image_processor.py	7.70 KB	482759e3bcc4e9bb5ee582b244cc563f5d0e163d8b48dda91ebb7106e62f9272
inference/kernel.py	23.8 KB	1236c3507019ed176f5dba5e04bcea58867cf654818c6cf138ed4845398c2455
inference/model.py	61.7 KB	e5decd76fe70fd56ef2f10124d245c6f64fb6a0003cc9068a1d3182a168b8d2d
inference/requirements.txt	98 B	be82bcd5775ccf8361ddd22cac53ef7b3b83434697fc3c61c75870450fb9437e
inference/run.sh	1.76 KB	91eddd7895f9fcd9bace53c21128c506e741e770f3c1a02464eff51f60401dfb
inference/vision.py	4.46 KB	5d49edc196a4ef22384abe76d35a40098cbe1e74b586c8f66a2edff4f076b26c
model-00001-of-00048.safetensors	971 MB	13bd121075f0b68cb7e8e8021a1011d42a81a83f557a2602fd9c07d52fddb0ec
model-00002-of-00048.safetensors	1.32 GB	43616eebd88dd4f1f1b642772356fc160478d1d9d04edd240431e7d065d2eda7
model-00003-of-00048.safetensors	7.39 GB	41611994fc9b27829b757d72257570d65a976fe65b8c6df8641adcd139d65ded
model-00004-of-00048.safetensors	7.39 GB	e8e901b3cb1ab46f32729c7eaab37bd774a09094f0a02c51a60e883f779f2c39
model-00005-of-00048.safetensors	7.41 GB	c5df71c02d6a22bcb20a0dbbcda9c6b65aa104f44415102a9a6a03bee92bb9de
model-00006-of-00048.safetensors	7.39 GB	a5d42afde2aee33619fb7a674b4c737c38d1f1d47a636a26f3edfb3b54164167
model-00007-of-00048.safetensors	7.39 GB	24856942add8f73f5e1fbaea1e9c9b6ff597fd1b4aa4651d789833dd3a5a2ab9
model-00008-of-00048.safetensors	7.39 GB	7bf5f7afb5d2bacad49feffb049989fb365d6dbf96986e76265bd7a7a3469564
model-00009-of-00048.safetensors	7.39 GB	e6ae47e9daca138fda8c04f833c8328eb21671c37d1c8e2c3f7a82aac26649f6
model-00010-of-00048.safetensors	7.39 GB	835e9a8b0a28cc571cb1cf9e6014b3d5eb84ac41990a8aa4519e1ac435d7e23c
model-00011-of-00048.safetensors	7.41 GB	5df968edefe59033e451ff8512bef57da2cf97b57b4e7a1380118489dd02915b
model-00012-of-00048.safetensors	7.39 GB	4f97bf292f58178ecdf593b55252a401d6e9102f18625a4fccc52b8ee57e7be0
model-00013-of-00048.safetensors	7.39 GB	1b8567854887396840eb5392ca763101308064a142cb36156159096e581659eb
model-00014-of-00048.safetensors	7.39 GB	e5ba6d7e4380728ad70b8208676075a898f80a64c3618060f1b81e4218a159d1
model-00015-of-00048.safetensors	7.39 GB	f4b29d936024e68f44fb14d0ffffb15b42b27be04b4a0296acdae695afa94c30
model-00016-of-00048.safetensors	7.39 GB	3aa67228351c80e708dab4ac7f6e56b19000649cce2cd655def3168a3de4115c
model-00017-of-00048.safetensors	7.41 GB	b704eec7b7aa1bad6c9d57fa7f61f2db28862e8e5fc2468fd9d872689c778c7d
model-00018-of-00048.safetensors	7.39 GB	1405cf03376739f46e72e6cdd4d404969f1b94c717bb01782a300e2fbbd17e29
model-00019-of-00048.safetensors	7.39 GB	a84beaded1913e8d6119ac111f25040c8ec42e59f200dbe04c3a991cac512669
model-00020-of-00048.safetensors	7.39 GB	038914f79cf5499da90f0bfb8e1b7761cc37d5f4dd132e2431a6d02c9fb9fdfe
model-00021-of-00048.safetensors	7.39 GB	2ba49f59c8cec144e41370f9f820f268899d0b5cd0501e881908ca65bccd2dc2
model-00022-of-00048.safetensors	7.39 GB	52f12cceca5e2fdd0191dfbd33b808b6c7ce844cf9351c119413c5ba3bcd28c8
model-00023-of-00048.safetensors	7.40 GB	d6e47e8b7147c64eb6619732694dda811e1a9f8af1894977919af9522724ca31
model-00024-of-00048.safetensors	7.39 GB	9d611d65374d37f5e02fdae14e680cb69bf55af8a8478802ac465b97c65be22b
model-00025-of-00048.safetensors	7.39 GB	8db532a7cbb23cd4b5aa775636ca13af95b758501290fb935074348f660a29cd
model-00026-of-00048.safetensors	7.39 GB	2d6d7261937d2a98c7398a55ed48dbf129d9b4f188aa9148e46ea9f720255115
model-00027-of-00048.safetensors	7.40 GB	8e76de6a5cdc7ac0923526d1c1a2e6459c55bbfa692793b29cdfe07b4f9fbc52
model-00028-of-00048.safetensors	7.39 GB	3c0e5ad6a4e8e811c1a55fd8f5b59c9fa329b241c671997c28fc7a01944d5a77
model-00029-of-00048.safetensors	7.39 GB	392a950bcb062b89f683abc52d49a17e92c66f80cd1cb6fb92b71091da75319b
model-00030-of-00048.safetensors	7.39 GB	0b44d1364e578fc26dc0cc86564e49a92871a51063fb7f2f3b51cb020de44ab0
model-00031-of-00048.safetensors	7.40 GB	d3230ffc32e11c5a34505c5acaeaff642aed5c770b297695e1f7a94071d361ac
model-00032-of-00048.safetensors	7.39 GB	96d284016ac885415859346d971c0de43bd9e7947337edfb53c34462866ef1d7
model-00033-of-00048.safetensors	7.39 GB	313953b3b6aaa6d4c60bbcfc177dda5d8d1380c9fe72d82560ba078f55278a8d
model-00034-of-00048.safetensors	7.39 GB	98eb27655774796bb3feadb35ec64a9849104b88c4c6ae7cabf6fc1ee317a056
model-00035-of-00048.safetensors	7.40 GB	4a321a28c048389039e4595641fe0b1f130428c61fc8f655545afe0083d37cd9
model-00036-of-00048.safetensors	7.39 GB	97c7910a8a14002dd941f45f6ddb2bd335eaf6fa05f4a76b2ff9285d6557b65d
model-00037-of-00048.safetensors	7.39 GB	d37ee013b805344619536e299c73adf92df03744aa0a242f2c5465590015e5be
model-00038-of-00048.safetensors	7.39 GB	7713bf7a78319eb1c6214b312e0a2da8cac88d77dce851d50f1113d78f8975a4
model-00039-of-00048.safetensors	7.40 GB	658a77d47d217995b9b78612e69ee0d0e33f6c2240f4ec629fecdca3ecb03f4c
model-00040-of-00048.safetensors	7.39 GB	6a9dbcc8d5894ba614b5e962764f45f6d0df7f14f1287b17f173d1f2cd762186
model-00041-of-00048.safetensors	7.39 GB	458308f08ed29b34850bd6b9d10bf769620729d3725c77f7bc0c1d14e01b47cc
model-00042-of-00048.safetensors	7.39 GB	3d283a4ed6eb2d5013bacc97c3500361926a3261957943434513304df52adfd7
model-00043-of-00048.safetensors	1.32 GB	4ae12b941c3facf8616ce62dd45bc6868076c2aeb82106f98123ea6c5bb64182
model-00044-of-00048.safetensors	2.65 GB	3e8ac315c2bcca3e83c5e6e25c5758a75c03732063a6ff0c1b0e24b9ff49f6e6
model-00045-of-00048.safetensors	2.57 GB	9c73b27c4343236790008979d5e0b565f687aa64440031b9e096fed1ab8039c5
model-00046-of-00048.safetensors	2.71 GB	1dccc19a3741972c661de734572dc7d4b899e6e99bfbdf3ae4e057c707e5b339
model-00047-of-00048.safetensors	102 GB	76a05106ece259be83d1bfea0dcb54f23377864ee60fd321690f35e6698a2af5
model-00048-of-00048.safetensors	102 GB	9dc51433e195bc78b5ad846b68643cc0351d3b174e5e4309222d3b7402c83afd
model.safetensors.index.json	7.47 MB	74b0686a3d2891980d5e303251b075a3bccae2c2ff650747db2620a649b98fa8
tokenizer.json	6.37 MB	c90dfa01249db1be4245780a052ede752e1361c612ac6d08e2bdada7d599476b
tokenizer_config.json	801 B	6ac8c8dc065ed118161d02dd532749ae3f52c243deac27872134fae2f50d8547

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
08c8657f02 pinned now	2026-11-14 06:27 UTC	84 files · 510 GB

Use it

$ fw get deepseek-ai/DeepSeek-V4.1-Flash-1017
# manifest sha256 90ed8b9a634d… · 510 GB · 84 files
$ fw verify ./DeepSeek-V4.1-Flash-1017 deepseek-ai/DeepSeek-V4.1-Flash-1017

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4.1-Flash-1017.json --dir ./DeepSeek-V4.1-Flash-1017
$ python3 fw.py verify ./DeepSeek-V4.1-Flash-1017 ./deepseek-ai__DeepSeek-V4.1-Flash-1017.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V4.1-Flash-1017 --revision 08c8657f02291e11b6f6b63e0e16014f8e748518 --local-dir ./DeepSeek-V4.1-Flash-1017

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForImageTextToText, AutoProcessor
processor = AutoProcessor.from_pretrained("deepseek-ai/DeepSeek-V4.1-Flash-1017", revision="08c8657f02291e11b6f6b63e0e16014f8e748518")
model = AutoModelForImageTextToText.from_pretrained("deepseek-ai/DeepSeek-V4.1-Flash-1017", revision="08c8657f02291e11b6f6b63e0e16014f8e748518", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve deepseek-ai/DeepSeek-V4.1-Flash-1017 --revision 08c8657f02291e11b6f6b63e0e16014f8e748518

Run at home

License

Name: MIT License
Id: MIT
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: Checked and recorded in the license audit. 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:

deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V4.1-Flash-1017Date: 2026-11-14Commit: 08c8657Signed: 2DC28CC7B26A283B ✓

Upstream: deepseek-ai/DeepSeek-V4.1-Flash-1017
Pinned commit: 08c8657f02291e11b6f6b63e0e16014f8e748518
Manifest: DeepSeek-V4.1-Flash-1017.json · .minisig
Manifest sha256: 90ed8b9a634d717727b3dcadb4471bee88dce6505cd2cdb43a7d9f44b81a6033
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 06:27 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4.1-Flash-1017.json
$ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V4.1-Flash-1017.json.minisig
$ minisign -Vm DeepSeek-V4.1-Flash-1017.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

12 models in the catalog name this one as their parent.

Quantizations: 12

Quantizations 12

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V4.1-Flash-1017

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.json. Provenance. Takedown history: none.

Source

huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017

Variants

12 quantized or adapter builds of DeepSeek-V4.1-Flash-1017. Each has its own license check and page.

SubjectSizeParamsLicenseDate

DeepSeek-V4.1-Flash-1017-GGUFHosted (signed) From: unsloth in alt.freeweights.deepseek4.06 TB—Permissive2026-11-14

DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUFHosted (signed) From: ISTA-DASLab in alt.freeweights.deepseek184 GB—Permissive2026-11-14

Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUFHosted (signed) From: huihui-ai in alt.freeweights.abliterated710 GB—Permissive2026-11-14

DeepSeek-V4.1-Flash-1017-oQ4e-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek432 GB129.1BPermissive2026-11-14

DeepSeek-V4.1-Flash-1017-oQ2.5e-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek343 GB102.4BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek512 GB288.8BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-GGUFHosted (signed) From: ggml-org in alt.freeweights.deepseek651 GB—Permissive2026-11-14

DeepSeek-V4.1-Flash-1017-oQ2e-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek313 GB95.1BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-oQ3e-ngram-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek461 GB271.8BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-oQ3e-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek381 GB112.1BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-oQ2.5e-ngram-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek423 GB262.2BPermissive2026-11-15

DeepSeek-V4.1-Flash-1017-oQ2e-ngram-mtpHosted (signed) From: mlx-community in alt.freeweights.deepseek393 GB254.8BPermissive2026-11-15

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

DeepSeek-V4.1-Flash-1017

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

DeepSeek-V4.1-Flash-1017#

Introduction#

Prompt Encoding#

Minimal Inference#

License#

Citation#

Contact#

Files

Use it

License

Provenance

How to verify

Model tree

Variants

Related models