alt.freeweights.deepseek / DeepSeek-V3-0324-GGUF
From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V3-0324-GGUF

Date: 2026-11-15Commit: 522a005Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 5.62 TB in all. Published by unsloth under MIT.

deepseek5.62TBDeepSeek-V3-0324-GGUFggufpermissive
FactsParamsnot statedSize5.62 TBFormatsggufTasktext generationLicenseMITFrom sourcepermissive
$ fw get unsloth/DeepSeek-V3-0324-GGUF
# manifest sha256 965a1a5f7f08… · 5.62 TB · 126 files
$ fw verify ./DeepSeek-V3-0324-GGUF unsloth/DeepSeek-V3-0324-GGUF
From sourceHosted (signed)unsloth/DeepSeek-V3-0324-GGUFLast check: 2026-11-15 04:55 UTC

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

Quantized of DeepSeek-V3-0324.

Works with

Convert with

Overview

Size
5.62 TB
Weights
186 GB (smallest of 13 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
MIT (permissive)
Files
126, each with a sha256
Publisher
unsloth
Added
2026-11-15
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Base model: deepseek-ai/DeepSeek-V3-0324

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 04:55 UTCpassed

Model card

From the publisher at commit 522a005. Shown as plain text with links; images open at the publisher.

Read our guide for detailed instructions on running DeepSeek-V3-0324 locally.

Unsloth's Dynamic Quants is selectively quantized, greatly improving accuracy over standard bits.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-v3-0324-locally

DeepSeek-V3-0324 Dynamic GGUF#

Our DeepSeek-V3-0324 GGUFs allow you to run the model in llama.cpp, LMStudio, Open WebUI and other inference frameworks.

Includes 1-4-bit Dynamic versions, which yields better accuracy and results than standard quantization.

MoE BitsTypeDisk SizeAccuracyLinkDetails
1.78bit (prelim)IQ1_S186GBOkLinkdown_proj in MoE mixture of 2.06/1.78bit
1.93bit (prelim)IQ1_M196GBFairLinkdown_proj in MoE mixture of 2.06/1.93bit
2.42bitIQ2_XXS219GBRecommendedLinkdown_proj in MoE all 2.42bit
2.71bitQ2_K_XL248GBRecommendedLinkdown_proj in MoE mixture of 3.5/2.71bit
3.5bitQ3_K_XL321GBGreatLinkdown_proj in MoE mixture of 4.5/3.5bit
4.5bitQ4_K_XL405GBBestLinkdown_proj in MoE mixture of 5.5/4.5bit

Prelim = preliminary - through our testing, they're generally fine but sometimes don't produce the best code and so more work/testing needs to be done. 2.71bit was found to be the best in terms of performance/size and produces code that is great and works well. 2.42bit was also found to pass all our tests.

So, for best results, use the 2.42-bit (IQ2_XXS) or 2.71-bit (Q2_K_XL) versions. Though not a must, try to have at least 180GB+ combined VRAM + RAM.

Thank you to the DeepSeek team for releasing their March update to the DeepSeek V3 models. Also thank you to bartowski for providing imatric V3 quants.

Finetune your own Reasoning model like R1 with Unsloth!#

We have a free Google Colab notebook for turning Llama 3.1 (8B) into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb

✨ Finetune for Free#

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supportsFree NotebooksPerformanceMemory use
GRPO with Phi-4 (14B)▶️ Start on Colab-GRPO.ipynb)2x faster80% less
Llama-3.2 (3B)▶️ Start on Colab-Conversational.ipynb)2.4x faster58% less
Llama-3.2 (11B vision)▶️ Start on Colab-Vision.ipynb)2x faster60% less
Qwen2 VL (7B)▶️ Start on Colab-Vision.ipynb)1.8x faster60% less
Qwen2.5 (7B)▶️ Start on Colab-Alpaca.ipynb)2x faster60% less
Llama-3.1 (8B)▶️ Start on Colab-Alpaca.ipynb)2.4x faster58% less
Phi-3.5 (mini)▶️ Start on Colab2x faster50% less
Gemma 2 (9B)▶️ Start on Colab-Alpaca.ipynb)2.4x faster58% less
Mistral (7B)▶️ Start on Colab-Conversational.ipynb)2.2x faster62% less

Image: DeepSeek-V3


Homepage Chat Hugging Face

Discord Wechat Twitter Follow

License

Features#

DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects.

Image: Model Performance

Reasoning Capabilities#
  • Significant improvements in benchmark performance:
    • MMLU-Pro: 75.9 → 81.2 (+5.3)
    • GPQA: 59.1 → 68.4 (+9.3)
    • AIME: 39.6 → 59.4 (+19.8)
    • LiveCodeBench: 39.2 → 49.2 (+10.0)
Front-End Web Development#
  • Improved the executability of the code
  • More aesthetically pleasing web pages and game front-ends
Chinese Writing Proficiency#
  • Enhanced style and content quality:
    • Aligned with the R1 writing style
    • Better quality in medium-to-long-form writing
  • Feature Enhancements
    • Improved multi-turn interactive rewriting
    • Optimized translation quality and letter writing
Chinese Search Capabilities#
  • Enhanced report analysis requests with more detailed outputs
Function Calling Improvements#
  • Increased accuracy in Function Calling, fixing issues from previous V3 versions

Usage Recommendations#

System Prompt#

In the official DeepSeek web/app, we use the same system prompt with a specific date.

该助手为DeepSeek Chat,由深度求索公司创造。
今天是{current date}。

For example,

该助手为DeepSeek Chat,由深度求索公司创造。
今天是3月24日,星期一。
Temperature#

In our web and application environments, the temperature parameter $T_{model}$ is set to 0.3. Because many users use the default temperature 1.0 in API call, we have implemented an API temperature $T_{api}$ mapping mechanism that adjusts the input API temperature value of 1.0 to the most suitable model temperature setting of 0.3.

$$ T_{model} = T_{api} \times 0.3 \quad (0 \leq T_{api} \leq 1) $$

$$ T_{model} = T_{api} - 0.7 \quad (1 < T_{api} \leq 2) $$

Thus, if you call V3 via API, temperature 1.0 equals to the model temperature 0.3.

For file uploading, please follow the template to create prompts, where {file_name}, {file_content} and {question} are arguments.

file_template = \
"""[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}"""

For Web Search, {search_results}, {cur_date}, and {question} are arguments.

For Chinese query, we use the prompt:

search_answer_zh_template = \
'''# 以下内容是基于用户发送的消息的搜索结果:
{search_results}
在我给你的搜索结果中,每个结果都是[webpage X begin]...[webpage X end]格式的,X代表每篇文章的数字索引。请在适当的情况下在句子末尾引用上下文。请按照引用编号[citation:X]的格式在答案中对应部分引用上下文。如果一句话源自多个上下文,请列出所有相关的引用编号,例如[citation:3][citation:5],切记不要将引用集中在最后返回引用编号,而是在答案对应部分列出。
在回答时,请注意以下几点:
- 今天是{cur_date}。
- 并非搜索结果的所有内容都与用户的问题密切相关,你需要结合问题,对搜索结果进行甄别、筛选。
- 对于列举类的问题(如列举所有航班信息),尽量将答案控制在10个要点以内,并告诉用户可以查看搜索来源、获得完整信息。优先提供信息完整、最相关的列举项;如非必要,不要主动告诉用户搜索结果未提供的内容。
- 对于创作类的问题(如写论文),请务必在正文的段落中引用对应的参考编号,例如[citation:3][citation:5],不能只在文章末尾引用。你需要解读并概括用户的题目要求,选择合适的格式,充分利用搜索结果并抽取重要信息,生成符合用户要求、极具思想深度、富有创造力与专业性的答案。你的创作篇幅需要尽可能延长,对于每一个要点的论述要推测用户的意图,给出尽可能多角度的回答要点,且务必信息量大、论述详尽。
- 如果回答很长,请尽量结构化、分段落总结。如果需要分点作答,尽量控制在5个点以内,并合并相关的内容。
- 对于客观类的问答,如果问题的答案非常简短,可以适当补充一到两句相关信息,以丰富内容。
- 你需要根据用户要求和回答内容选择合适、美观的回答格式,确保可读性强。
- 你的回答应该综合多个相关网页来回答,不能重复引用一个网页。
- 除非用户要求,否则你回答的语言需要和用户提问的语言保持一致。

# 用户消息为:
{question}'''

For English query, we use the prompt:

search_answer_en_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.

# The user's message is:
{question}'''

How to Run Locally#

The model structure of DeepSeek-V3-0324 is exactly the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

This model supports features such as function calling, JSON output, and FIM completion. For instructions on how to construct prompts to use these features, please refer to DeepSeek-V2.5 repo.

NOTE: Hugging Face's Transformers has not been directly supported yet.

License#

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

Citation#

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}

Contact#

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

Files

126 files · 5.62 TBWeights 186 GB (smallest of 13 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 126 files with their sha256
FileSizesha256
.gitattributes13.3 KBf6361aadac448914b48ef6ef284be629d1841780cc6e97d38fefe55279b6128d
BF16/DeepSeek-V3-0324-BF16-00001-of-00030.gguf43.9 GB77643061a0d0f3661709fca3125508c9e9fd21240ac2ab83e3616eb232b28f67
BF16/DeepSeek-V3-0324-BF16-00002-of-00030.gguf46.0 GB5cc2ea755f2dd2c0f7023f34e58842accfa51d7db2a21fcafd6a958dce4a5659
BF16/DeepSeek-V3-0324-BF16-00003-of-00030.gguf46.0 GBa1fb3bc9eb7af42b832bae430cd725fa73d5f9ef890dfe0b0044d748ad541fb8
BF16/DeepSeek-V3-0324-BF16-00004-of-00030.gguf46.0 GB94c9a7db24f83cc811cfa11fc57c509c32d46abc32764b7683595815305c908f
BF16/DeepSeek-V3-0324-BF16-00005-of-00030.gguf46.0 GB308465e92d338319a8ccd5e381ccda1e46e139affe7ce47738b4cc3a36ced390
BF16/DeepSeek-V3-0324-BF16-00006-of-00030.gguf46.0 GB803502b94968103f5a7444bde5ebbbef7a46f1007f132dbcf8b91102a49d491f
BF16/DeepSeek-V3-0324-BF16-00007-of-00030.gguf46.0 GB0ef97e2b0757df84d146aac606fd19c62b91edfa0cada3e04e525cc23859962e
BF16/DeepSeek-V3-0324-BF16-00008-of-00030.gguf46.0 GBf8e7cf73a1444f768094d6dff982a2bb1a2688b0aaef26eec632b3c8ffeaa401
BF16/DeepSeek-V3-0324-BF16-00009-of-00030.gguf46.0 GB881f6f22c441d3560c56970df3eb7caa51b485602f36c944e22ff97a9a7a187c
BF16/DeepSeek-V3-0324-BF16-00010-of-00030.gguf46.0 GB3e590013b11469e8f872a7aaaf63ea1f759a6a813ed15ee75aab2a6addee6142
BF16/DeepSeek-V3-0324-BF16-00011-of-00030.gguf46.0 GB96c0650fe4082134bf10bca2ed952e32388ca97f2e0df31d1805aaea9ba20554
BF16/DeepSeek-V3-0324-BF16-00012-of-00030.gguf46.0 GB10a56019bc500a15bee89682e499b34842aa8d717fd299e0b588bf292cad03bc
BF16/DeepSeek-V3-0324-BF16-00013-of-00030.gguf46.0 GB70f45f52112e523aca6c411e84e35398fe6c88db97497a1da3158276f8de2916
BF16/DeepSeek-V3-0324-BF16-00014-of-00030.gguf46.0 GBd3df6d9a76221794f01b29a52e048ae8afd66f5d69ad105e50782c974f5e28e1
BF16/DeepSeek-V3-0324-BF16-00015-of-00030.gguf46.0 GBeebd7c59e508cf7dab3dc93b4ad026c33c3ed395e5c5c292de36e732fe1a0eb1
BF16/DeepSeek-V3-0324-BF16-00016-of-00030.gguf46.0 GB7f212b772a7bbafd24c39e9c56ccd55dedb4491a1a60202f347d458d5b4f242d
BF16/DeepSeek-V3-0324-BF16-00017-of-00030.gguf46.0 GBa58e3fb1f56da7431e3429e792831afdb7fe13c95d6bb2b89226ab4e7d796acb
BF16/DeepSeek-V3-0324-BF16-00018-of-00030.gguf46.0 GB9697b7c7dcb2d6e66ee4b7eedad0e1b762bac10f457b4a4f32caf3cf67eeb053
BF16/DeepSeek-V3-0324-BF16-00019-of-00030.gguf46.0 GB254cdc2284c176923e5649aaf85347733d0598bc674a53443b94298c30bc3594
BF16/DeepSeek-V3-0324-BF16-00020-of-00030.gguf46.0 GBcbfaac4b906c8804dffbb3ec635c4f555e6fdd7ab13b74586a5fbad8c118d34f
BF16/DeepSeek-V3-0324-BF16-00021-of-00030.gguf46.0 GB06d82e1f2daef4071d1012eac212f34ec6d64ed293d81603f9b5c1a39f9c5deb
BF16/DeepSeek-V3-0324-BF16-00022-of-00030.gguf46.0 GB7b6edc0a0759b5bc231ddff1a55b60f1e2eacc32da5326eef203950264047843
BF16/DeepSeek-V3-0324-BF16-00023-of-00030.gguf46.0 GBc4849dd30d855efe56c5306ffe15687746f155759475ea579398064fad9b9bc5
BF16/DeepSeek-V3-0324-BF16-00024-of-00030.gguf46.0 GB5fa806cf007082fe849c34513fa8a2c1b5637d379a9dc1b3d40f1ca79cc0de12
BF16/DeepSeek-V3-0324-BF16-00025-of-00030.gguf46.0 GB1b283000b74ae4a2ce0d98e373ada67dc8f11e985f8cc2b0112025508050f7ac
BF16/DeepSeek-V3-0324-BF16-00026-of-00030.gguf46.0 GB25ebe7023d162d7a708c3b5558aeeef9b728e09f38d7bc2d9ff79caa2b7ac7e8
BF16/DeepSeek-V3-0324-BF16-00027-of-00030.gguf46.0 GBf0a2e1573fde22616a8b607e3e4e85cbc2d72d66a3e6a3ab8d6cbbcb42c54cc1
BF16/DeepSeek-V3-0324-BF16-00028-of-00030.gguf46.0 GB96dfe10115086c3a62b3c46f9f1c95c5d9d65e943e2546be8ec2bab9d35d45f9
BF16/DeepSeek-V3-0324-BF16-00029-of-00030.gguf47.9 GB434ccdb4bb8eaea3a633a2d22bab6200e9b8794ba061c7f17f4bc6723b777306
BF16/DeepSeek-V3-0324-BF16-00030-of-00030.gguf7.52 GB35c2ed6472dd394eb6a8ec334b9f40af084281d9d43eddc6dcbe8444110bc585
Q2_K/DeepSeek-V3-0324-Q2_K-00001-of-00005.gguf49.4 GB52237cb4203ae2aa3c7df0859fa8db0e59c331023e2854d11de083e1f729c153
Q2_K/DeepSeek-V3-0324-Q2_K-00002-of-00005.gguf48.5 GB5ec493b947ad88123f98f0f503b6351c80a5a51dff99b846cc2fbd4647b797a5
Q2_K/DeepSeek-V3-0324-Q2_K-00003-of-00005.gguf48.8 GB237f1f75cee758a1529514e2aa03f6c853ad7754f0e830a3fd33fe8b05663bc3
Q2_K/DeepSeek-V3-0324-Q2_K-00004-of-00005.gguf48.9 GB4c7c629b1cb6de99656641ae56ad10c2c0bb00d98bcab791a40d9fdce5041cfe
Q2_K/DeepSeek-V3-0324-Q2_K-00005-of-00005.gguf48.4 GB6b8346b6a2786c4cad7f2112b1d610e1aa65fe1b6188751c96c0ce9ae59cb960
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00001-of-00007.gguf49.7 GBac9d3805ed6086378e363898404d5ce82dc6e84ae71ce8a5e74cbbf53663da1c
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00002-of-00007.gguf49.2 GB9c77e19e0562bcb6f13802f6857d5d0425f0abe8fa40b0894e9b823cc95ec326
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00003-of-00007.gguf49.2 GB67b04fa86b032fe4afa8bfd23a43f0b226f84231c80708fcbaba8eefffa79259
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00004-of-00007.gguf49.2 GBaa604f485bc1def74c1fcb2ec5b7cd096575b4dbc48c6ff3605014b9e59f6e93
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00005-of-00007.gguf49.2 GB4fa595bce9a75a3f9e1bd9850130eb6f08534f94d962d7c26f3549c3433e3765
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00006-of-00007.gguf49.2 GB521c2d3bb34699951ecfb2506f2cde532f04d293ef17ccc28c492d0716bd0fd1
Q3_K_M/DeepSeek-V3-0324-Q3_K_M-00007-of-00007.gguf23.5 GBc76895f3634cef693a98d2cf651f69e3332a2f0f95669f23e25357eaa70bfb63
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00001-of-00009.gguf48.3 GB02381ba6cb2e0b5ba4924b6be1938d0f47ac0253c356b684b7497591c4d434fe
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00002-of-00009.gguf49.4 GB7b435d3d19e1cdeac905d87a0a164bc27c8d9a73b556d833a10dbb9db9ad394a
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00003-of-00009.gguf49.5 GBd13cf5f74dced9269bf6d184f3ed9fe99c34f7b3de204274f301ca796fc3a07a
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00004-of-00009.gguf48.3 GB86b7067284e2658ab58b3275796ed03e3922ce2eb86e43e170587feaa181fa89
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00005-of-00009.gguf49.4 GBcc4d169bcba80e0d1202ab6468dc18995926042b679eeb03e517f5c5418ad3c0
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00006-of-00009.gguf48.3 GB7743bdc666153c30c6f62cfe62e257fbf8f40e045d869ea10f5a5bbc4a7de9a0
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00007-of-00009.gguf49.4 GBefdb60fce78fc7bcab1377cef5795e12c6a0ecf0dc5c47a274502aca90100e0c
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00008-of-00009.gguf46.9 GBcde24cd28c4f69eb562c8b82d9568cc4eca9728583dfc128e5a2ed4845c5f6bc
Q4_K_M/DeepSeek-V3-0324-Q4_K_M-00009-of-00009.gguf14.8 GB514ce763f6106996f0a21e6f89d556b51d8947310e9fa6e6791bc70ec7b6b23b
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00001-of-00010.gguf49.6 GB3a1fd13f61dc17ab3e5a1b6f8d73390acc5cae36c6a8741e32040519ce68984b
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00002-of-00010.gguf48.5 GB84e8614f0696443d04e8b31739922f960ca9837f4aa199d4b75b9af48de265f3
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00003-of-00010.gguf48.5 GBdb657e111a648e15328fb47dc0e50ade96bc162679670f9deb3fb12b44ddd64a
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00004-of-00010.gguf48.5 GBf8ddf3018c75e7955617e794d2cd2fdec3d92410b559960144442c73cc2a32cc
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00005-of-00010.gguf48.5 GB7a855e529690fbf8504bb47a88587243f58fc05a9a9944b70866828f7c2608cc
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00006-of-00010.gguf48.5 GB13899d58e2c13a6005928b9dc4ccfc48f543db955396882a6ebcbd2749e7b06b
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00007-of-00010.gguf48.5 GB4b76fc595be23703f6092cb051136df7c4c6cf317b30433d5540cfc49b944b1a
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00008-of-00010.gguf48.5 GB379b3dc2c215918442649d00a85430c4fbaa551de858c965c57a566815c911dc
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00009-of-00010.gguf50.0 GBe026951941323f399668efe99ab3647f0d8baaa39b1d4881b8bef8c8afabfe65
Q5_K_M/DeepSeek-V3-0324-Q5_K_M-00010-of-00010.gguf36.3 GBaca14897a0164d540f3cab79940c5fd9664363c307c43949c3911d6377f89160
Q6_K/DeepSeek-V3-0324-Q6_K-00001-of-00012.gguf47.1 GB912f894b79597237d809a5e6034f09ffabfca78e321438e74bc2bf0b37f5bdb2
Q6_K/DeepSeek-V3-0324-Q6_K-00002-of-00012.gguf47.2 GB3c47d9a1933722505157935c299b89485e6de8a2f86ff61146777deae9d13213
Q6_K/DeepSeek-V3-0324-Q6_K-00003-of-00012.gguf47.2 GBfe8b8b5b37f4f6597563246b3192537f4a51bd0b0f25120fefb7fa1cea261dc0
Q6_K/DeepSeek-V3-0324-Q6_K-00004-of-00012.gguf47.2 GBfce68bb41db1530b02c6bdfe2b19cef392922ecc2e04df1e2b31314b878c5ef4
Q6_K/DeepSeek-V3-0324-Q6_K-00005-of-00012.gguf47.2 GB5a2c07235c80a9039d59f9f365c70a830c5144e89cb8d3ed9dc0fab39a0683ff
Q6_K/DeepSeek-V3-0324-Q6_K-00006-of-00012.gguf47.2 GB580b1c3dcd1ba43bda874b5e0373930ebaf737e83a2752092967075418e77d6f
Q6_K/DeepSeek-V3-0324-Q6_K-00007-of-00012.gguf47.2 GBd03b6f8897a19f08bbbb2fcf16760c6d3616ba089c078fa2cb25f7956d481f29
Q6_K/DeepSeek-V3-0324-Q6_K-00008-of-00012.gguf47.2 GB617d9e94e91b67fafc3417692e68ca69049f0313143c6e17616ca0da8ae2aefe
Q6_K/DeepSeek-V3-0324-Q6_K-00009-of-00012.gguf47.2 GB42927844820ae7f91701617bf39024109eda9338bea4f40a99d47c4f62c0cb3e
Q6_K/DeepSeek-V3-0324-Q6_K-00010-of-00012.gguf47.2 GB8fef82962924c0a8b6e3ea07df6b3def1912a747a4c0172a792c603b817ed3af
Q6_K/DeepSeek-V3-0324-Q6_K-00011-of-00012.gguf47.2 GBc40dd87ff4f3e097041f32d187ba4377c1544a1e2df35f9d5bfe70ea589bd844
Q6_K/DeepSeek-V3-0324-Q6_K-00012-of-00012.gguf31.4 GB66631b3864ca7601d31fe0346161b62b91da5ce98dff1b42e051ab904e55df8c
Q8_0/DeepSeek-V3-0324-Q8_0-00001-of-00015.gguf47.8 GBb5f44cf0cec2a4e2591ff32c117e43caeec047f18caee434cf2fb290e51b8460
Q8_0/DeepSeek-V3-0324-Q8_0-00002-of-00015.gguf48.9 GB7fe3a37fc8ed537b8318bea1514ea6be5ac1063e829021a0d740da4f930d60ab
Q8_0/DeepSeek-V3-0324-Q8_0-00003-of-00015.gguf48.9 GB31a8ee605f5b60f60263de10db6c59b704ecf6157082a95827bd42b8d5c4d7e0
Q8_0/DeepSeek-V3-0324-Q8_0-00004-of-00015.gguf48.9 GB737263cf2cd68d4e3b253b5adeab975cb84afa8358f5751fa06f9cd4bd25a50a
Q8_0/DeepSeek-V3-0324-Q8_0-00005-of-00015.gguf48.9 GBb477700ef9bbb95e0937559b602ad939e6cb78526cdc8386419cb3910886765a
Q8_0/DeepSeek-V3-0324-Q8_0-00006-of-00015.gguf48.9 GB4afd6a5bdfa089de2c60ec1f7713c7215d0e9c33215d10c1b9af0556541e5160
Q8_0/DeepSeek-V3-0324-Q8_0-00007-of-00015.gguf48.9 GBb760d5c46356a37566ae594ad1bc0555b655575628208f53f775d71642aae6e1
Q8_0/DeepSeek-V3-0324-Q8_0-00008-of-00015.gguf48.9 GBc6b4cc76fabefaebee8387e423ee5470549ac883a0e9731a1138898e430fc43e
Q8_0/DeepSeek-V3-0324-Q8_0-00009-of-00015.gguf48.9 GBc795cd80d99ec7694b6c306dcdc3085056a888b9c17d8ad7c3041d0346c99a7d
Q8_0/DeepSeek-V3-0324-Q8_0-00010-of-00015.gguf48.9 GBd1ab30e7e972990be1397c10130e00063eb847a2a4d282d0106969eb529c877d
Q8_0/DeepSeek-V3-0324-Q8_0-00011-of-00015.gguf48.9 GBd694fd44410959436ecbb6a073c55a773441fa7a530ab95461d94f93df35f684
Q8_0/DeepSeek-V3-0324-Q8_0-00012-of-00015.gguf48.9 GB57800b15ff908514bf1ac84463ebf8239fe2e518f81fc9a928f8cf892ae67de9
Q8_0/DeepSeek-V3-0324-Q8_0-00013-of-00015.gguf48.9 GBa605f9600e1c726b6649c873b0c9705a755fdf48fd21a75f64aaa22c09079e00
Q8_0/DeepSeek-V3-0324-Q8_0-00014-of-00015.gguf48.9 GBdf60f71ed38b9f12b3a1ffd982ed00f87de32fbb50d33e13d4e1b75861c06af6
Q8_0/DeepSeek-V3-0324-Q8_0-00015-of-00015.gguf29.4 GBff91c16b82188fc50ec81236916ca87e0ca1484da2b5569a246e21acb0e11d86
README.md17.0 KB6c0954d00496da52100a57fbc15101a96a1bf18099e973e21817d95eaa5870e8
UD-IQ1_M/DeepSeek-V3-0324-UD-IQ1_M-00001-of-00004.gguf49.5 GB35b0acd89edd1a0998ed398dd994ac3ffb498557438507b50e6b3f6fa8105a3b
UD-IQ1_M/DeepSeek-V3-0324-UD-IQ1_M-00002-of-00004.gguf49.5 GB57a3342695018d5735844812894209ee52a84c8ca3140d5fc113f600a25f792c
UD-IQ1_M/DeepSeek-V3-0324-UD-IQ1_M-00003-of-00004.gguf49.4 GB365d2cf4ea3b4eed9e29a8f6d5e4b3071e8f1db436ef1ab3495d5afd24223093
UD-IQ1_M/DeepSeek-V3-0324-UD-IQ1_M-00004-of-00004.gguf48.1 GB0c2b76082455dad896cb1e116ee1b3d49560a9b90cafbdee4769b6002f295010
UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00001-of-00004.gguf48.6 GBa0a6642eb5f4cd378fdb2b637b89126a88e8ab2a510cf05224b5f300d983d98d
UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00002-of-00004.gguf48.5 GB8faceb0370c0fa0ced2b410027955520c710d892dfa793297c0d8ec022375496
UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00003-of-00004.gguf48.5 GB881849206d4ff8a562f5a2711f1c620abcbdfd2014dc912ff4c6f03d028b6fbf
UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00004-of-00004.gguf40.6 GB11fc8abfc5ef7051e2d9e8c5adb27408db0c80541fa5bd50d16021a8cd61dcff
UD-IQ2_XXS/DeepSeek-V3-0324-UD-IQ2_XXS-00001-of-00005.gguf48.4 GB9657df221eef4c23676908ed02130cca139b18d205445bc9bb766403c4d12cab
UD-IQ2_XXS/DeepSeek-V3-0324-UD-IQ2_XXS-00002-of-00005.gguf49.8 GBed0441d9be781291b311a812beb52b0aa156f303d9200ca43d21bf0195c82869
UD-IQ2_XXS/DeepSeek-V3-0324-UD-IQ2_XXS-00003-of-00005.gguf49.1 GB69f4f8d5301354c5b6c4f93550c0590d33e4b7075627daa56f563ae97413f146
UD-IQ2_XXS/DeepSeek-V3-0324-UD-IQ2_XXS-00004-of-00005.gguf49.2 GBbf6038ff3c144a26eb56fa24e30100500007b85dc685b86fe2686d660ec2f533
UD-IQ2_XXS/DeepSeek-V3-0324-UD-IQ2_XXS-00005-of-00005.gguf22.1 GB9a0dfafa182a2bc9f40d8d9cb2885ae5543a757f46f2a399daa361051e72f607
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00001-of-00006.gguf49.0 GBa175fb9082806ffae03c890b9a2daae46d24f39b616e0e9d9908f9b212e0ab76
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00002-of-00006.gguf49.4 GB2aa680995be7c46d423515477261fabdda9cbca7cbc60bba877a58143fdb7582
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00003-of-00006.gguf49.5 GB66fcda6a99d901b5fa4c5ff0eabff57af035d09ebb9f4e6ed41ad6926ef9cd0d
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00004-of-00006.gguf49.1 GB63ac78c8363784885a985beff75e375c6bb63f6b31ff905b2ac5df0267f3e389
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00005-of-00006.gguf49.4 GBd3e6cdee637bd94744c971ffb8df34064a8a26ac0fc2e60e8321b427373a8ca6
UD-Q2_K_XL/DeepSeek-V3-0324-UD-Q2_K_XL-00006-of-00006.gguf1.24 GB28c72c67d74403ea758faf93217672b0a14d2bb32d21b4bf1d53846ae7f8b536
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00001-of-00007.gguf48.5 GBcaea123845e9bcaa5032e352fcd8a615ad5a0d06f3314434bbf2fcc9a5ac65af
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00002-of-00007.gguf49.4 GB2f71b9152359b090fd3ef2c9aedf23d52278302a5fa0f7802851264ecee51869
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00003-of-00007.gguf49.4 GBf7bddc8f251097f299dd74211cf036760e18dea288183156babcb550ff16121c
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00004-of-00007.gguf49.4 GB612cb34f95fa3552a01c1c1a9ae664c76e8aa51b2f24aaa8ea93de2562a2f898
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00005-of-00007.gguf49.4 GB24158bc98b4977fb3c4064ec599d688e21b8483037588b4a301f7e9f517acb21
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00006-of-00007.gguf49.4 GBbb38f388402429c1db2a5f29dcb684ff411ae9585ba435641efc0e3ef5f64c79
UD-Q3_K_XL/DeepSeek-V3-0324-UD-Q3_K_XL-00007-of-00007.gguf25.2 GBf88fc71568a9e2f3d4e1f9e17fdd6c85423b507bc4a92e7f08bbb566a5c28734
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00001-of-00009.gguf48.4 GBf5eb5dfd4aad0d9a782fed22381146c7be5ab9e07be90bde82f6745faf365946
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00002-of-00009.gguf49.5 GB7ce7c85ab02ccde5cb7fee0a0b67d4e15989a1f45b492fa09c12a18d89289fac
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00003-of-00009.gguf49.6 GB30adf58f57b73342c34db16c6a49dcc0e6291dd7f0c1c4471795ab6c829e5aea
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00004-of-00009.gguf48.3 GBd5ef64b6aaf24461fe023b706571ec163454029d5825a93652afda0f79139a68
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00005-of-00009.gguf49.5 GB6e67da4d7577531fdcf24e61fbf364dac8c4dbd5c99fc669e0561cfee8789a59
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00006-of-00009.gguf48.3 GB1de47b831b49fb0d87fe544086070a80c1bec191683cbe6797a11f30b36fa3eb
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00007-of-00009.gguf49.5 GB4d807247056e0717a4e9edd1899d35b64969054865c2ff625ab3a16aa8743a81
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00008-of-00009.gguf47.0 GB041dc2d6a1106a3212d829d2cd0840f6bf50f89ac99196a9fca187afc0c2d023
UD-Q4_K_XL/DeepSeek-V3-0324-UD-Q4_K_XL-00009-of-00009.gguf14.8 GB563f785959a4c8bf5772df2d4a041e9d6419b924243cfd37b0bb5fadc8b50b08
config.json1.73 KB4422016f41c506339e0510a32812a63da554dc9febd5f1368e7240ded14e4a27
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
522a005de3 pinned now2026-11-15 04:55 UTC126 files · 5.62 TB

Use it

$ fw get unsloth/DeepSeek-V3-0324-GGUF
# manifest sha256 965a1a5f7f08… · 5.62 TB · 126 files
$ fw verify ./DeepSeek-V3-0324-GGUF unsloth/DeepSeek-V3-0324-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/DeepSeek-V3-0324-GGUF.json --dir ./DeepSeek-V3-0324-GGUF $ python3 fw.py verify ./DeepSeek-V3-0324-GGUF ./unsloth__DeepSeek-V3-0324-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/DeepSeek-V3-0324-GGUF --revision 522a005de381512eeb3e22aff4232335431f7303 --local-dir ./DeepSeek-V3-0324-GGUF
llama.cppDownload one GGUF variant (UD-IQ1_S, 186 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/DeepSeek-V3-0324-GGUF --include "UD-IQ1_S/*" --local-dir ./DeepSeek-V3-0324-GGUF $ llama-server -m ./DeepSeek-V3-0324-GGUF/UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00001-of-00004.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-V3-0324-GGUF/UD-IQ1_S/DeepSeek-V3-0324-UD-IQ1_S-00001-of-00004.gguf\n' > Modelfile $ ollama create deepseek-v3-0324-gguf -f Modelfile

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
README.md
Text sha256
6c0954d00496da52100a57fbc15101a96a1bf18099e973e21817d95eaa5870e8
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: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V3-0324-GGUFDate: 2026-11-15Commit: 522a005Signed: 2DC28CC7B26A283B ✓
Upstream
unsloth/DeepSeek-V3-0324-GGUF
Pinned commit
522a005de381512eeb3e22aff4232335431f7303
Manifest
DeepSeek-V3-0324-GGUF.json · .minisig
Manifest sha256
965a1a5f7f084124f7d0298cda34f26b5bfddc2903566f2431e58e0dcaf4d5e2
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:55 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/DeepSeek-V3-0324-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/DeepSeek-V3-0324-GGUF.json.minisig $ minisign -Vm DeepSeek-V3-0324-GGUF.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-V3-0324 · 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 unsloth/DeepSeek-V3-0324-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V3-0324-GGUF.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