Ir para o conteúdo
ModelVerificadoExterno
Baixar

Qwen3.5 122B A10B REAP 20 I1 GGUF

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

Fontehuggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/tree/a2c1bbb5fe1ca4a9c3182a31a40a3c8129d33883
TipoOtherModelo base0xSero/Qwen3.5-99BVersãoRevision a2c1bbbPublicador@mradermacherCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
275 MB–75,7 GB
Modelo base
0xSero/Qwen3.5-99B
Versão
vRevision a2c1bbb
Atualizado
3 de out. de 2026
Publicador
@mradermacher
Downloads
1,1 mil
Parâmetros
122B
Fonte
Hugging Face

Descrição da fonte

About

weighted/imatrix quants of https://huggingface.co/0xSero/Qwen3.5-99B

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

static quants are available at https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

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_S20.8for the desperate
GGUFi1-IQ1_M23.0mostly desperate
GGUFi1-IQ2_XXS26.7
GGUFi1-IQ2_XS29.6
GGUFi1-IQ2_S30.0
GGUFi1-IQ2_M32.9
GGUFi1-Q2_K_S34.3very low quality
GGUFi1-Q2_K36.6IQ3_XXS probably better
GGUFi1-IQ3_XXS38.6lower quality
GGUFi1-IQ3_XS41.0
GGUFi1-Q3_K_S43.1IQ3_XS probably better
GGUFi1-IQ3_S43.2beats Q3_K*
GGUFi1-IQ3_M43.8
GGUFi1-Q3_K_M47.7IQ3_S probably better
GGUFi1-Q3_K_L51.5IQ3_M probably better
GGUFi1-IQ4_XS53.3
GGUFi1-Q4_056.4fast, low quality
GGUFi1-Q4_K_S56.6optimal size/speed/quality
GGUFi1-Q4_K_M60.3fast, recommended
GGUFi1-Q4_162.2
GGUFi1-Q5_K_S68.4
GGUFi1-Q5_K_M70.5
GGUFi1-Q6_K81.4practically 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.

Fontes

1 fonte
Hugging FacePrimárioVersão a2c1bbb5fe1ca4a9c3182a31a40a3c8129d33883
huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/tree/a2c1bbb5fe1ca4a9c3182a31a40a3c8129d33883

Verificado 2 de out.

Artefatos de modelo

24 artefatos

Qwen3.5-122B-A10B-REAP-20.i1-IQ1_M.gguf

gguf · 21,4 GB · SHA-256 b930aa8bf33d…1a6e · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ1_S.gguf

gguf · 19,3 GB · SHA-256 1819482b924e…e0c4 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ2_M.gguf

gguf · 30,5 GB · SHA-256 e282c727d1cf…69d1 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ2_S.gguf

gguf · 27,8 GB · SHA-256 af3fe50c83fb…327a · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ2_XS.gguf

gguf · 27,5 GB · SHA-256 356705189e5e…5073 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ2_XXS.gguf

gguf · 24,8 GB · SHA-256 7f986a7db3c1…f79d · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ3_M.gguf

gguf · 40,7 GB · SHA-256 3a019573b54c…52e3 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ3_S.gguf

gguf · 40,2 GB · SHA-256 0e390d353eee…7881 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ3_XS.gguf

gguf · 38,1 GB · SHA-256 6a640b3bec30…6999 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ3_XXS.gguf

gguf · 35,9 GB · SHA-256 b83f0e3f3396…fc7c · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-IQ4_XS.gguf

gguf · 49,5 GB · SHA-256 1478210b9498…c5bd · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q2_K_S.gguf

gguf · 31,9 GB · SHA-256 82c5fc0f89b0…5999 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q2_K.gguf

gguf · 34,0 GB · SHA-256 bff279ee0855…03c4 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q3_K_L.gguf

gguf · 47,9 GB · SHA-256 74f19e2e1864…24fa · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q3_K_M.gguf

gguf · 44,3 GB · SHA-256 0a201e96e5d5…157d · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q3_K_S.gguf

gguf · 40,0 GB · SHA-256 0728350db38d…6ff2 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q4_0.gguf

gguf · 52,4 GB · SHA-256 0ab4aa051bca…25bb · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q4_1.gguf

gguf · 57,9 GB · SHA-256 d126934493e9…5989 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q4_K_M.gguf

gguf · 56,1 GB · SHA-256 87f778d93fb9…81f1 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q4_K_S.gguf

gguf · 52,6 GB · SHA-256 0d44dcc4ed46…9c98 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q5_K_M.gguf

gguf · 65,6 GB · SHA-256 9fe497dfd0ff…d574 · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q5_K_S.gguf

gguf · 63,6 GB · SHA-256 cf62c72ef4e1…352d · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.i1-Q6_K.gguf

gguf · 75,7 GB · SHA-256 684bdc839c9e…a1dc · Hugging Face

Baixar

Qwen3.5-122B-A10B-REAP-20.imatrix.gguf

gguf · 275 MB · SHA-256 0d4e9bf3e9d4…24dd · Hugging Face

Baixar

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF

--- base_model: 0xSero/Qwen3.5-99B language: - en library_name: transformers license: other mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - expert-pruning - moe - pruned - qwen3.5 - reap --- ## 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: 1 --> weighted/imatrix quants of https://huggingface.co/0xSero/Qwen3.5-99B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3.5-122B-A10B-REAP-20-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-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/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/resolve/main/Qwen3.5-122B-A10B-REAP-20.imatrix.gguf) | imatrix | 0.4 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/resolve/main/Qwen3.5-122B-A10B-REAP-20.i1-IQ1_S.gguf) | i1-IQ1_S | 20.8 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/resolve/main/Qwen3.5-122B-A10B-REAP-20.i1-IQ1_M.gguf) | i1-IQ1_M | 23.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/resolve/main/Qwen3.5-122B-A10B-REAP-20.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 26.7 | | | [GGUF](https://huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF/resolve/main/Qwen3.5-122B-A10B-REAP-20.i1-IQ2_XS.gguf) | i1-IQ2_XS | 29.6 | | | [GGUF](https:/...

Note2 de out.huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF

Source context: 1134 downloads · 4 likes · Library transformers · Repo mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF

Note17 de jul.huggingface.co/mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF

Source context: 6791 downloads · 4 likes · Library transformers · Repo mradermacher/Qwen3.5-122B-A10B-REAP-20-i1-GGUF