Skip to content
ModelVerifiedExternal
Browse files

VisReason Qwen2.5 VL 7B GGUF

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

Sourcehuggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/tree/76be64d66745aed8783f5128d49b0d75f58751fe
KindOtherBase modelY-Research-Group/VisReason-Qwen2.5-VL-7BVersionRevision 76be64dPublisher@mradermacherCgrade

Model source

Kind
Other
File size
816 MB–14.2 GB
Base model
Y-Research-Group/VisReason-Qwen2.5-VL-7B
Version
vRevision 76be64d
Updated
Oct 29, 2026
Publisher
@mradermacher
Downloads
948
Parameters
7B
Source
Hugging Face

Source description

About

static quants of https://huggingface.co/Y-Research-Group/VisReason-Qwen2.5-VL-7B

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-i1-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
GGUFmmproj-Q8_01.0multi-modal supplement
GGUFmmproj-f161.5multi-modal supplement
GGUFQ2_K3.1
GGUFQ3_K_S3.6
GGUFQ3_K_M3.9lower quality
GGUFQ3_K_L4.2
GGUFIQ4_XS4.4
GGUFQ4_K_S4.6fast, recommended
GGUFQ4_K_M4.8fast, recommended
GGUFQ5_K_S5.4
GGUFQ5_K_M5.5
GGUFQ6_K6.4very good quality
GGUFQ8_08.2fast, best quality
GGUFf1615.316 bpw, overkill

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.

Sources

1 source
Hugging FacePrimaryVersion 76be64d66745aed8783f5128d49b0d75f58751fe
huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/tree/76be64d66745aed8783f5128d49b0d75f58751fe

Verified Oct 29

Download files

Model artifacts

14 artifacts

VisReason-Qwen2.5-VL-7B.f16.gguf

gguf · 14.2 GB · SHA-256 ff0c58863672…0870 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.IQ4_XS.gguf

gguf · 3.96 GB · SHA-256 bcc1a749c1df…097e · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.mmproj-f16.gguf

gguf · 1.26 GB · SHA-256 de6212cd443e…9239 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.mmproj-Q8_0.gguf

gguf · 816 MB · SHA-256 5a4135d8f2d5…11a8 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q2_K.gguf

gguf · 2.81 GB · SHA-256 7936e250f692…7d40 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q3_K_L.gguf

gguf · 3.81 GB · SHA-256 dbc0cf6fbdb8…e5aa · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q3_K_M.gguf

gguf · 3.55 GB · SHA-256 23eccc8b62ea…9498 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q3_K_S.gguf

gguf · 3.25 GB · SHA-256 c71cb05a2d97…7c06 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q4_K_M.gguf

gguf · 4.36 GB · SHA-256 6dc8cf662d9f…36b3 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q4_K_S.gguf

gguf · 4.15 GB · SHA-256 c5f1edabd2e8…91c7 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q5_K_M.gguf

gguf · 5.07 GB · SHA-256 0bfcc2a96465…8a9a · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q5_K_S.gguf

gguf · 4.95 GB · SHA-256 19710a3dfe9a…e7d1 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q6_K.gguf

gguf · 5.82 GB · SHA-256 cb081fe25134…4704 · Hugging Face

Download file

VisReason-Qwen2.5-VL-7B.Q8_0.gguf

gguf · 7.54 GB · SHA-256 06a89bc64563…e54b · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF

--- base_model: Y-Research-Group/VisReason-Qwen2.5-VL-7B datasets: - Y-Research-Group/VisReason language: - en library_name: transformers license: other mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - visual-chain-of-thought - visual-reasoning - multimodal - grounding - qwen2_5_vl --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/Y-Research-Group/VisReason-Qwen2.5-VL-7B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VisReason-Qwen2.5-VL-7B-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-i1-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/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolve/main/VisReason-Qwen2.5-VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | | [GGUF](https://huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF/resolv...

NoteOct 29huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF

Source context: 948 downloads · 1 likes · Library transformers · Repo mradermacher/VisReason-Qwen2.5-VL-7B-GGUF

NoteJul 17huggingface.co/mradermacher/VisReason-Qwen2.5-VL-7B-GGUF

Source context: 652 downloads · 0 likes · Library transformers · Repo mradermacher/VisReason-Qwen2.5-VL-7B-GGUF