Zum Inhalt springen
ModelÜberprüftExtern
Herunterladen

Qwen3 Coder 57B I1 GGUF

For a convenient overview and download list, visit our model page for this model.

Quellehuggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/tree/e30fe50a8f78f1d85fa3b89c12d9560559dbb60b
ArtOtherBasismodell0xSero/Qwen3-Coder-57BVersionRevision e30fe50Verleger@mradermacherCBewertung

Modellquelle

Art
Other
Dateigröße
307 MB–43,3 GB
Basismodell
0xSero/Qwen3-Coder-57B
Version
vRevision e30fe50
Aktualisiert
23. Okt. 2026
Verleger
@mradermacher
Downloads
832
Parameter
57B
Quelle
Hugging Face

Quellenbeschreibung

About

weighted/imatrix quants of https://huggingface.co/0xSero/Qwen3-Coder-57B

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen3-Coder-57B-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

LinkTypeSize/GBNotes
GGUFimatrix0.4imatrix file (for creating your own quants)
GGUFi1-IQ1_S11.9for the desperate
GGUFi1-IQ1_M13.1mostly desperate
GGUFi1-IQ2_XXS15.2
GGUFi1-IQ2_XS16.9
GGUFi1-IQ2_S17.1
GGUFi1-IQ2_M18.8
GGUFi1-Q2_K_S19.6very low quality
GGUFi1-Q2_K20.9IQ3_XXS probably better
GGUFi1-IQ3_XXS22.1lower quality
GGUFi1-IQ3_XS23.5
GGUFi1-Q3_K_S24.7IQ3_XS probably better
GGUFi1-IQ3_S24.7beats Q3_K*
GGUFi1-IQ3_M25.1
GGUFi1-Q3_K_M27.3IQ3_S probably better
GGUFi1-Q3_K_L29.5IQ3_M probably better
GGUFi1-IQ4_XS30.5
GGUFi1-Q4_032.3fast, low quality
GGUFi1-Q4_K_S32.4optimal size/speed/quality
GGUFi1-Q4_K_M34.5fast, recommended
GGUFi1-Q4_135.6
GGUFi1-Q5_K_S39.2
GGUFi1-Q5_K_M40.4
GGUFi1-Q6_K46.6practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Quellen

1 Quelle
Hugging FacePrimärVersion e30fe50a8f78f1d85fa3b89c12d9560559dbb60b
huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/tree/e30fe50a8f78f1d85fa3b89c12d9560559dbb60b

Verifiziert 23. Okt.

Modellartefakte

24 Artefakte

Qwen3-Coder-57B.i1-IQ1_M.gguf

gguf · 12,1 GB · SHA-256 2b667d40994a…9a86 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ1_S.gguf

gguf · 11,0 GB · SHA-256 e94348cfaf0e…a23b · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ2_M.gguf

gguf · 17,4 GB · SHA-256 5515b9dfee85…9718 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ2_S.gguf

gguf · 15,8 GB · SHA-256 06d6573f4cbf…e9c4 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ2_XS.gguf

gguf · 15,7 GB · SHA-256 431ed66b7c75…bb05 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ2_XXS.gguf

gguf · 14,1 GB · SHA-256 202ef6243882…b727 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ3_M.gguf

gguf · 23,2 GB · SHA-256 ce84582d26f9…4b09 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ3_S.gguf

gguf · 23,0 GB · SHA-256 b011cf6c9e39…e1e1 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ3_XS.gguf

gguf · 21,8 GB · SHA-256 995d1a6989c5…c0bb · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ3_XXS.gguf

gguf · 20,5 GB · SHA-256 9c02629b0706…f63f · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-IQ4_XS.gguf

gguf · 28,3 GB · SHA-256 5c05fd8bb81b…30ea · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q2_K_S.gguf

gguf · 18,2 GB · SHA-256 bd841e8a0102…f772 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q2_K.gguf

gguf · 19,4 GB · SHA-256 561e8a3fb906…8874 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q3_K_L.gguf

gguf · 27,4 GB · SHA-256 4a760ea5396d…409b · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q3_K_M.gguf

gguf · 25,3 GB · SHA-256 eb99643c2d7d…f018 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q3_K_S.gguf

gguf · 22,9 GB · SHA-256 16a819ddeb48…f775 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q4_0.gguf

gguf · 30,0 GB · SHA-256 2537f5e1f07d…ac05 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q4_1.gguf

gguf · 33,1 GB · SHA-256 abf57904d465…94d5 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q4_K_M.gguf

gguf · 32,1 GB · SHA-256 c0e18f0d38d9…8149 · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q4_K_S.gguf

gguf · 30,1 GB · SHA-256 7ae8873e60aa…01dc · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q5_K_M.gguf

gguf · 37,5 GB · SHA-256 406b590278eb…0f8a · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q5_K_S.gguf

gguf · 36,4 GB · SHA-256 2d62e2a0a405…d2fb · Hugging Face

Herunterladen

Qwen3-Coder-57B.i1-Q6_K.gguf

gguf · 43,3 GB · SHA-256 0032601d7129…4c4a · Hugging Face

Herunterladen

Qwen3-Coder-57B.imatrix.gguf

gguf · 307 MB · SHA-256 dea9f70b6d37…50e6 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge
Readme11. Julihuggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF

--- base_model: 0xSero/Qwen3-Coder-57B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - cerebras - expert-pruning - moe - pruning - qwen3 - qwen3-coder - qwen3_next - reap - safetensors --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/0xSero/Qwen3-Coder-57B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Coder-57B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Qwen3-Coder-57B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.imatrix.gguf) | imatrix | 0.4 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.i1-IQ1_S.gguf) | i1-IQ1_S | 11.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.i1-IQ1_M.gguf) | i1-IQ1_M | 13.1 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 15.2 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 16.9 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-57B.i1-IQ2_S.gguf) | i1-IQ2_S | 17.1 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF/resolve/main/Qwen3-Coder-5...

Note23. Okt.huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF

Source context: 832 downloads · 0 likes · Library transformers · Repo mradermacher/Qwen3-Coder-57B-i1-GGUF

Note6. Aug.huggingface.co/mradermacher/Qwen3-Coder-57B-i1-GGUF

Source context: 183 downloads · 0 likes · Library transformers · Repo mradermacher/Qwen3-Coder-57B-i1-GGUF