steampunque/Qwen2.5-VL-7B-Instruct-Hybrid-GGUF

Llama.cpp hybrid layer quantization of Qwen2.5-VL-7B-Instruct by Alibaba

Original model: https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct

The hybrid quant employs different quantization levels on a per layer basis to enable both high performance and small file size at the same time. This particular quant achieves a ~5.7G gguf with the same perplexity as a ~6.3G Q6_K GGUF. The quants employed are all K to avoid slow CPU or older GPU processing of IQ quants. For this file the layer quants are as follows:

   LAYER_TYPES='[
   [0 ,"Q6_K"  ],[1 ,"Q5_K_M"],[2 ,"Q4_K_M"],[3 ,"Q4_K_M"],[4 ,"Q4_K_M"],[5 ,"Q4_K_M"],[6 ,"Q5_K_S"],
   [7 ,"Q5_K_S"],[8 ,"Q5_K_S"],[9 ,"Q5_K_S"],[10,"Q5_K_M"],[11,"Q5_K_S"],[12,"Q5_K_M"],[13,"Q5_K_S"],
   [14,"Q5_K_M"],[15,"Q5_K_M"],[16,"Q5_K_M"],[17,"Q5_K_M"],[18,"Q5_K_M"],[19,"Q5_K_M"],[20,"Q5_K_M"],
   [21,"Q5_K_M"],[22,"Q6_K"  ],[23,"Q6_K"  ],[24,"Q6_K"  ],[25,"Q8_0"  ],[26,"Q8_0"  ],[27,"Q8_0"  ]
   ]'
   FLAGS="--token-embedding-type Q6_K --output-tensor-type Q6_K"

Comparison:

Quant	size	PPL	Comment
Q6_K	6.25e9	9.7	Q6_K with default embedding and output
Q6_K_H	5.73e9	9.7	Hybrid quant with Q6_K embedding Q6_K output

Usage:

Qwen2.5-VL-7B-Instruct is a vision capable model. It can be used together with its multimedia projector layers to process images and text inputs and generate text outputs. The mmproj file is made available in this repository. To test vision mode follow the docs in the mtmd readme in the tools directory of the source tree https://github.com/ggml-org/llama.cpp/blob/master/tools/mtmd/README.md .

Benchmarks:

A full set of benchmarks for the model will eventually be given here: https://huggingface.co/spaces/steampunque/benchlm

Download the file from below:

Link	Type	Size/e9 B	Notes
Qwen2.5-VL-7B-Instruct.Q6_K_H.gguf	Q6_K_H	5.73e9 B	0.5B smaller than Q6_K
Qwen2.5-VL-7B-Instruct.mmproj.gguf	mmproj	1.35e9 B	multimedia projector

A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

https://github.com/ggml-org/llama.cpp/discussions/13040