Zum Inhalt springen
ModelÜberprüftExtern
Browse files

Qwen3 32B Instruct TextOnly I1 GGUF

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

Quellehuggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/tree/914c8b750699e08b94d00212c5c1d193315a9350
ArtOtherBasismodellrpDungeon/Qwen3-32B-Instruct-TextOnlyVersionRevision 914c8b7Verleger@mradermacherCBewertung

Modellquelle

Art
Other
Dateigröße
14,6 MB–25,0 GB
Basismodell
rpDungeon/Qwen3-32B-Instruct-TextOnly
Version
vRevision 914c8b7
Aktualisiert
3. Okt. 2026
Verleger
@mradermacher
Downloads
477
Parameter
32B
Quelle
Hugging Face

Quellenbeschreibung

About

weighted/imatrix quants of https://huggingface.co/rpDungeon/Qwen3-32B-Instruct-TextOnly

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

static quants are available at https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-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
GGUFimatrix0.1imatrix file (for creating your own quants)
GGUFi1-IQ1_S7.4for the desperate
GGUFi1-IQ1_M8.1mostly desperate
GGUFi1-IQ2_XXS9.1
GGUFi1-IQ2_XS10.1
GGUFi1-IQ2_S10.6
GGUFi1-IQ2_M11.5
GGUFi1-Q2_K_S11.6very low quality
GGUFi1-Q2_K12.4IQ3_XXS probably better
GGUFi1-IQ3_XXS12.9lower quality
GGUFi1-IQ3_XS13.8
GGUFi1-Q3_K_S14.5IQ3_XS probably better
GGUFi1-IQ3_S14.5beats Q3_K*
GGUFi1-IQ3_M15.0
GGUFi1-Q3_K_M16.1IQ3_S probably better
GGUFi1-Q3_K_L17.4IQ3_M probably better
GGUFi1-IQ4_XS17.8
GGUFi1-Q4_018.8fast, low quality
GGUFi1-Q4_K_S18.9optimal size/speed/quality
GGUFi1-Q4_K_M19.9fast, recommended
GGUFi1-Q4_120.7
GGUFi1-Q5_K_S22.7
GGUFi1-Q5_K_M23.3
GGUFi1-Q6_K27.0practically 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 914c8b750699e08b94d00212c5c1d193315a9350
huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/tree/914c8b750699e08b94d00212c5c1d193315a9350

Verifiziert 3. Okt.

Download files

Modellartefakte

24 Artefakte

Qwen3-32B-Instruct-TextOnly.i1-IQ1_M.gguf

gguf · 7,41 GB · SHA-256 46ea2ab1c227…536e · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ1_S.gguf

gguf · 6,82 GB · SHA-256 73efb837cf27…72f9 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ2_M.gguf

gguf · 10,6 GB · SHA-256 48aff8c3099a…3e84 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ2_S.gguf

gguf · 9,79 GB · SHA-256 51de58c4567e…894e · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ2_XS.gguf

gguf · 9,27 GB · SHA-256 55863c799b34…ad9d · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ2_XXS.gguf

gguf · 8,40 GB · SHA-256 a86ad47e0025…53f9 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ3_M.gguf

gguf · 13,9 GB · SHA-256 9a5cda132696…0a88 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ3_S.gguf

gguf · 13,4 GB · SHA-256 5b0deb74a9a1…1d3f · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ3_XS.gguf

gguf · 12,8 GB · SHA-256 cf55aa73789d…1021 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ3_XXS.gguf

gguf · 11,9 GB · SHA-256 78dcd7c0459a…78ca · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-IQ4_XS.gguf

gguf · 16,5 GB · SHA-256 b2a2c7ff1350…8541 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q2_K_S.gguf

gguf · 10,7 GB · SHA-256 a4a3d6f66fce…b12b · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q2_K.gguf

gguf · 11,5 GB · SHA-256 5c107e3f4975…31ad · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q3_K_L.gguf

gguf · 16,1 GB · SHA-256 fad363357e18…beef · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q3_K_M.gguf

gguf · 14,9 GB · SHA-256 7942db8ae7b6…6c38 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q3_K_S.gguf

gguf · 13,4 GB · SHA-256 95d4cb7cf9b4…be67 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q4_0.gguf

gguf · 17,4 GB · SHA-256 60f749a9f875…3c87 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q4_1.gguf

gguf · 19,2 GB · SHA-256 534a91d94156…8911 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q4_K_M.gguf

gguf · 18,4 GB · SHA-256 3c5756d61692…bda1 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q4_K_S.gguf

gguf · 17,5 GB · SHA-256 50c546a7abed…e99f · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q5_K_M.gguf

gguf · 21,6 GB · SHA-256 70a2362758ec…9ee3 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q5_K_S.gguf

gguf · 21,1 GB · SHA-256 3ca15dccdb2d…6d32 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.i1-Q6_K.gguf

gguf · 25,0 GB · SHA-256 ae411a75b32d…14f7 · Hugging Face

Download file

Qwen3-32B-Instruct-TextOnly.imatrix.gguf

gguf · 14,6 MB · SHA-256 3691f5196ac5…bc21 · Hugging Face

Download file

Quellenauszüge

3 Auszüge
Readme11. Julihuggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF

--- base_model: rpDungeon/Qwen3-32B-Instruct-TextOnly language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## 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/rpDungeon/Qwen3-32B-Instruct-TextOnly <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-32B-Instruct-TextOnly-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-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/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF/resolve/main/Qwen3-32B-Instruct-TextOnly.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | | [GGUF](https://huggingfa...

Note3. Okt.huggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF

Source context: 477 downloads · 0 likes · Library transformers · Repo mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF

Note17. Julihuggingface.co/mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF

Source context: 131 downloads · 0 likes · Library transformers · Repo mradermacher/Qwen3-32B-Instruct-TextOnly-i1-GGUF