Quantization made by Richard Erkhov.

Qwen2-VL-7B-Instruct-bnb-4bit-r4-90 - GGUF

Name	Quant method	Size
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q2_K.gguf	Q2_K	2.81GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.IQ3_XS.gguf	IQ3_XS	3.12GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.IQ3_S.gguf	IQ3_S	3.26GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q3_K_S.gguf	Q3_K_S	3.25GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.IQ3_M.gguf	IQ3_M	3.33GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q3_K.gguf	Q3_K	3.55GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q3_K_M.gguf	Q3_K_M	3.55GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q3_K_L.gguf	Q3_K_L	3.81GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.IQ4_XS.gguf	IQ4_XS	3.96GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q4_0.gguf	Q4_0	4.13GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.IQ4_NL.gguf	IQ4_NL	4.16GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q4_K_S.gguf	Q4_K_S	4.15GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q4_K.gguf	Q4_K	4.36GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q4_K_M.gguf	Q4_K_M	4.36GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q4_1.gguf	Q4_1	4.54GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q5_0.gguf	Q5_0	4.95GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q5_K_S.gguf	Q5_K_S	4.95GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q5_K.gguf	Q5_K	5.07GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q5_K_M.gguf	Q5_K_M	5.07GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q5_1.gguf	Q5_1	5.36GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q6_K.gguf	Q6_K	5.82GB
Qwen2-VL-7B-Instruct-bnb-4bit-r4-90.Q8_0.gguf	Q8_0	7.54GB

Original model description:

Developed by: akshaya-244
License: apache-2.0
Finetuned from model: unsloth/Qwen2-VL-7B-Instruct-bnb-4bit

base_model: unsloth/Qwen2-VL-7B-Instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - qwen2_vl

This qwen2_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.