CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.deepseek / DeepSeek-R1-Distill-Qwen-7B-GGUF
From: bartowski <huggingface.co/bartowski>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-R1-Distill-Qwen-7B-GGUF

Date: 2026-11-14Commit: 3610041Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 148 GB in all. Published by bartowski under MIT.

deepseek148GBDeepSeek-R1-Distill-Qwen-7B-GGUFggufpermissive
FactsParamsnot statedSize148 GBFormatsggufTasktext generationLicenseMITFrom sourcepermissive
$ fw get bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
# manifest sha256 757387011443… · 148 GB · 28 files
$ fw verify ./DeepSeek-R1-Distill-Qwen-7B-GGUF bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
From sourceHosted (signed)bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUFLast check: 2026-11-14 21:27 UTC
Run at homeGet help

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

Quantized of DeepSeek-R1-Distill-Qwen-7B.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
148 GB
Weights
2.78 GB (smallest of 24 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
MIT (permissive)
Files
28, each with a sha256
Publisher
bartowski
Added
2026-11-14
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

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 21:27 UTCpassed

Model card

From the publisher at commit 3610041. Shown as plain text with links; images open at the publisher.

Llamacpp imatrix Quantizations of DeepSeek-R1-Distill-Qwen-7B#

Using llama.cpp release b4514 for quantization.

Original model: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format#

<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜>

Download a file (not the whole branch) from below:#

FilenameQuant typeFile SizeSplitDescription
DeepSeek-R1-Distill-Qwen-7B-f32.gguff3230.47GBfalseFull F32 weights.
DeepSeek-R1-Distill-Qwen-7B-f16.gguff1615.24GBfalseFull F16 weights.
DeepSeek-R1-Distill-Qwen-7B-Q8_0.ggufQ8_08.10GBfalseExtremely high quality, generally unneeded but max available quant.
DeepSeek-R1-Distill-Qwen-7B-Q6_K_L.ggufQ6_K_L6.52GBfalseUses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q6_K.ggufQ6_K6.25GBfalseVery high quality, near perfect, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q5_K_L.ggufQ5_K_L5.78GBfalseUses Q8_0 for embed and output weights. High quality, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.ggufQ5_K_M5.44GBfalseHigh quality, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.ggufQ5_K_S5.32GBfalseHigh quality, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q4_K_L.ggufQ4_K_L5.09GBfalseUses Q8_0 for embed and output weights. Good quality, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q4_1.ggufQ4_14.87GBfalseLegacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.ggufQ4_K_M4.68GBfalseGood quality, default size for most use cases, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q3_K_XL.ggufQ3_K_XL4.57GBfalseUses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.ggufQ4_K_S4.46GBfalseSlightly lower quality with more space savings, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q4_0.ggufQ4_04.44GBfalseLegacy format, offers online repacking for ARM and AVX CPU inference.
DeepSeek-R1-Distill-Qwen-7B-IQ4_NL.ggufIQ4_NL4.44GBfalseSimilar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
DeepSeek-R1-Distill-Qwen-7B-IQ4_XS.ggufIQ4_XS4.22GBfalseDecent quality, smaller than Q4_K_S with similar performance, recommended.
DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.ggufQ3_K_L4.09GBfalseLower quality but usable, good for low RAM availability.
DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.ggufQ3_K_M3.81GBfalseLow quality.
DeepSeek-R1-Distill-Qwen-7B-IQ3_M.ggufIQ3_M3.57GBfalseMedium-low quality, new method with decent performance comparable to Q3_K_M.
DeepSeek-R1-Distill-Qwen-7B-Q2_K_L.ggufQ2_K_L3.55GBfalseUses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.ggufQ3_K_S3.49GBfalseLow quality, not recommended.
DeepSeek-R1-Distill-Qwen-7B-IQ3_XS.ggufIQ3_XS3.35GBfalseLower quality, new method with decent performance, slightly better than Q3_K_S.
DeepSeek-R1-Distill-Qwen-7B-Q2_K.ggufQ2_K3.02GBfalseVery low quality but surprisingly usable.
DeepSeek-R1-Distill-Qwen-7B-IQ2_M.ggufIQ2_M2.78GBfalseRelatively low quality, uses SOTA techniques to be surprisingly usable.

Embed/output weights#

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli#

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF --include "DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF --include "DeepSeek-R1-Distill-Qwen-7B-Q8_0/*" --local-dir ./

You can either specify a new local-dir (DeepSeek-R1-Distill-Qwen-7B-Q8_0) or download them all in place (./)

ARM/AVX information#

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Click to view Q4_0_X_X information (deprecated

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

Click to view benchmarks on an AVX2 system (EPYC7702)

modelsizeparamsbackendthreadstestt/s% (vs Q4_0)
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp512204.03 ± 1.03100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp1024282.92 ± 0.19100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64pp2048259.49 ± 0.44100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg12839.12 ± 0.27100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg25639.31 ± 0.69100%
qwen2 3B Q4_01.70 GiB3.09 BCPU64tg51240.52 ± 0.03100%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp512301.02 ± 1.74147%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp1024287.23 ± 0.20101%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64pp2048262.77 ± 1.81101%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg12818.80 ± 0.9948%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg25624.46 ± 3.0483%
qwen2 3B Q4_K_M1.79 GiB3.09 BCPU64tg51236.32 ± 3.5990%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp512271.71 ± 3.53133%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp1024279.86 ± 45.63100%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64pp2048320.77 ± 5.00124%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg12843.51 ± 0.05111%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg25643.35 ± 0.09110%
qwen2 3B Q4_0_8_81.69 GiB3.09 BCPU64tg51242.60 ± 0.31105%

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

Which file should I choose?#

Click here for details

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.

Credits#

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Files

28 files · 148 GBWeights 2.78 GB (smallest of 24 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 28 files with their sha256
FileSizesha256
.gitattributes3.40 KB35e34990c61435c7b7c79836c60a4109d650966df09c991f3bad12e8b47cb5b1
DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf2.78 GBf1f4aeac22ffb5a076e1a7e7b2c472445e213ec559a8b8fe91284881ed5aafec
DeepSeek-R1-Distill-Qwen-7B-IQ3_M.gguf3.57 GB75cec730a54922436496349ba19bcf86170d378180c27e019640aae722754598
DeepSeek-R1-Distill-Qwen-7B-IQ3_XS.gguf3.35 GB0b7758a3bab29000411c0775c51e791075468978252a2564f91422d38f39c76d
DeepSeek-R1-Distill-Qwen-7B-IQ4_NL.gguf4.44 GB7e115905a753c8191f8a76c91f83a1f9742387bd5187eef65f5c7ca6b556cc10
DeepSeek-R1-Distill-Qwen-7B-IQ4_XS.gguf4.22 GB23bc628ca6c45627e166c483587ce8bf73d050d4e3932a3f6908b5fbdcc5c7af
DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf3.02 GBfb0667a00ac788f4450c42457cc3f03be548d567454775b848dc85d8bc8a7837
DeepSeek-R1-Distill-Qwen-7B-Q2_K_L.gguf3.55 GB6fed62cc49e72adbc93d85f91aecaa50a7c4775fdf3846b8bbc38d600da0f5ec
DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf4.09 GBb80e42a5bc777dd781f8c9de9284d077d1cbf49157b811c854b6bfbedfed9853
DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf3.81 GB5c4f966a3b2907e08734dff2bea87acb01ec868a07ca1d8f7e30a3c6c62a98f3
DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf3.49 GBb0dfeda6e681c5257befd7b8a3553b476b347d1d74f42e33392b0abc9f12ddd4
DeepSeek-R1-Distill-Qwen-7B-Q3_K_XL.gguf4.57 GB3c3628e85101925c6e09f0ac25590ad80b4cf1e9b61068244a1d71731fabf041
DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf4.44 GB5cd4ee65211770f1d99b4f6f4951780b9ef40e29314bd6542bb5bd0ad0bc29d1
DeepSeek-R1-Distill-Qwen-7B-Q4_1.gguf4.87 GBde7784ba576e53c0f0a69ad93fcd47a05d9451743ba32612a2e9d16faff58da9
DeepSeek-R1-Distill-Qwen-7B-Q4_K_L.gguf5.09 GB47829fecccf67ec34b5b6d1951dad53174e1da535ff2f7816582db5ac731ed9c
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf4.68 GB731ece8d06dc7eda6f6572997feb9ee1258db0784827e642909d9b565641937b
DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf4.46 GBcfa2f69fd2983569515ebad512152c352c89043cbf2644b771ca4343b1d7b072
DeepSeek-R1-Distill-Qwen-7B-Q5_K_L.gguf5.78 GB49e2a43a0d66589286e7147cf0b623301e5f765310c5a5b7032ed4c4f04a327e
DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf5.44 GB7b736fc4913dce4c7fbcebe5cb965a2fa7314a14b59e25fb53d415f9d18d7aa1
DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf5.32 GBe8c1fb3b9052e677bcac767cf6745c4441a80b5e0ba3ca0d110083f361760ee1
DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf6.25 GB3ffa00e72db05668453687d5ab8e7c9fb19705cfd57292a956db17a3633c93f3
DeepSeek-R1-Distill-Qwen-7B-Q6_K_L.gguf6.52 GB40269ad1f7e65b2edb63580a9000e161c867e1d4cfea7a53aa80a83c4bf49ffc
DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf8.10 GBcae89f90c4c2f1894c95393903d2a9776aea7083023ae6cd285b1cc7adafc323
DeepSeek-R1-Distill-Qwen-7B-f16.gguf15.2 GBa11a09387d9e7a2c4d39143ca8bf6fe131e9040d2768bd86d4efb1fdecb12474
DeepSeek-R1-Distill-Qwen-7B-f32.gguf30.5 GBb027cb5f24756a91c8e349d3fceed20179c69fc17c024395cd4714695c66f3c4
DeepSeek-R1-Distill-Qwen-7B.imatrix4.54 MB476bee803c07f214c1d75f25979845d33472a964c54ca699bc85232306196f7b
LICENSE1.06 KB1c8f573e830ca9b3ebfeb7ace1823146e22b66f99ee223840e7637c9e745e1c7
README.md14.1 KB108a7416cfcf69967ada8205f4e72c7725331e34c76ac4446091d6dc7c9766fe
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
361004151d pinned now manifest updated, same commit2026-11-14 21:27 UTC28 files · 148 GB
361004151d2026-11-14 21:27 UTC28 files · 148 GB

Use it

$ fw get bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
# manifest sha256 757387011443… · 148 GB · 28 files
$ fw verify ./DeepSeek-R1-Distill-Qwen-7B-GGUF bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF.json --dir ./DeepSeek-R1-Distill-Qwen-7B-GGUF $ python3 fw.py verify ./DeepSeek-R1-Distill-Qwen-7B-GGUF ./bartowski__DeepSeek-R1-Distill-Qwen-7B-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF --revision 361004151d4f4f6b446dc5e6d46fbf4422a80d5f --local-dir ./DeepSeek-R1-Distill-Qwen-7B-GGUF
llama.cppDownload one GGUF variant (DeepSeek-R1-Distill-Qwen-7B-IQ2_M, 2.78 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF --include "DeepSeek-R1-Distill-Qwen-7B-IQ2_M*" --local-dir ./DeepSeek-R1-Distill-Qwen-7B-GGUF $ llama-server -m ./DeepSeek-R1-Distill-Qwen-7B-GGUF/DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./DeepSeek-R1-Distill-Qwen-7B-GGUF/DeepSeek-R1-Distill-Qwen-7B-IQ2_M.gguf\n' > Modelfile $ ollama create deepseek-r1-distill-qwen-7b-gguf -f Modelfile
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
Inherited from the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-7B: the strictest license along the lineage applies. 2026-11-14
Text in
LICENSE
Text sha256
1c8f573e830ca9b3ebfeb7ace1823146e22b66f99ee223840e7637c9e745e1c7
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: bartowski <huggingface.co/bartowski>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-R1-Distill-Qwen-7B-GGUFDate: 2026-11-14Commit: 3610041Signed: 2DC28CC7B26A283B ✓
Upstream
bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
Pinned commit
361004151d4f4f6b446dc5e6d46fbf4422a80d5f
Manifest
DeepSeek-R1-Distill-Qwen-7B-GGUF.json · .minisig
Manifest sha256
757387011443f3ba969c9212407571fb621538ab802a2bac86262dccf522d472
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:27 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF.json.minisig $ minisign -Vm DeepSeek-R1-Distill-Qwen-7B-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-R1-Distill-Qwen-7B · 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 bartowski/DeepSeek-R1-Distill-Qwen-7B-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-R1-Distill-Qwen-7B-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF

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