ModelListedExternal

UI Venus 1.5 2B GGUF

These are quantizations of the model UI-Venus-1.5-2B, using a imatrix created from text\en\medium

Sourcehuggingface.co/noctrex/UI-Venus-1.5-2B-GGUF/tree/42af01579dbcd9a2269b29db6e478e455d711509

KindOtherBase modelinclusionAI/UI-Venus-1.5-2BVersionRevision 42af015

Model source

Kind: Other
File size: 2.00 MB–3.79 GB
Base model: inclusionAI/UI-Venus-1.5-2B
Version: vRevision 42af015
Updated: Sep 26, 2026
Downloads: 188
Tasks: Captioning
Source: Hugging Face

Source description

These are quantizations of the model UI-Venus-1.5-2B, using a imatrix created from text_en_medium

Usage Notes:

Download the latest llama.cpp to use these quantizations.
Try to use the best quality you can run.
For the mmproj file, the F32 version is recommended for best results (F32 > BF16 > F16).

Sources

1 source

Hugging FacePrimaryVersion 42af01579dbcd9a2269b29db6e478e455d711509

huggingface.co/noctrex/UI-Venus-1.5-2B-GGUF/tree/42af01579dbcd9a2269b29db6e478e455d711509

Verified Sep 11

Download files

Model artifacts

12 artifacts

imatrix.gguf

gguf · 2.00 MB · SHA-256 ed756c809bd9…6d56 · Hugging Face

Download file

mmproj-BF16.gguf

gguf · 784 MB · SHA-256 ab43219eb969…55ec · Hugging Face

Download file

mmproj-F16.gguf

gguf · 781 MB · SHA-256 df84ad7622d7…2ecd · Hugging Face

Download file

mmproj-F32.gguf

gguf · 1.52 GB · SHA-256 bbff7a89c072…d781 · Hugging Face

Download file

UI-Venus-1.5-2B-BF16.gguf

gguf · 3.79 GB · SHA-256 8498a6fca637…c392 · Hugging Face

Download file

UI-Venus-1.5-2B-F16.gguf

gguf · 3.79 GB · SHA-256 f62defbed357…75b9 · Hugging Face

Download file

UI-Venus-1.5-2B-IQ4_NL.gguf

gguf · 1.15 GB · SHA-256 c791b0bb9ddb…8949 · Hugging Face

Download file

UI-Venus-1.5-2B-IQ4_XS.gguf

gguf · 1.09 GB · SHA-256 42b93a4c5676…92e8 · Hugging Face

Download file

UI-Venus-1.5-2B-Q4_K_M.gguf

gguf · 1.19 GB · SHA-256 2e20249b0d13…cf29 · Hugging Face

Download file

UI-Venus-1.5-2B-Q5_K_M.gguf

gguf · 1.37 GB · SHA-256 d0283498ece8…e540 · Hugging Face

Download file

UI-Venus-1.5-2B-Q6_K.gguf

gguf · 1.56 GB · SHA-256 7eaaf09bc2cc…be9c · Hugging Face

Download file

UI-Venus-1.5-2B-Q8_0.gguf

gguf · 2.02 GB · SHA-256 c50482bb36c6…c5f7 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeSep 11huggingface.co/noctrex/UI-Venus-1.5-2B-GGUF

--- pipeline_tag: image-to-text base_model: - inclusionAI/UI-Venus-1.5-2B --- These are quantizations of the model [UI-Venus-1.5-2B](https://huggingface.co/inclusionAI/UI-Venus-1.5-2B), using a imatrix created from [text\_en\_medium](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/text_en_medium.parquet) **Usage Notes:** - Download the latest [llama.cpp](https://github.com/ggml-org/llama.cpp) to use these quantizations. - Try to use the best quality you can run. - For the `mmproj` file, the F32 version is recommended for best results (F32 > BF16 > F16).

NoteSep 11huggingface.co/noctrex/UI-Venus-1.5-2B-GGUF

Source context: 188 downloads · 2 likes · Pipeline image-to-text · Repo noctrex/UI-Venus-1.5-2B-GGUF