Quantization made by Richard Erkhov.

Github

Discord

Request more models

qwen2.5-7B-Instruct-v0.2.9-v0.3 - GGUF

• Model creator: https://huggingface.co/RTX3090x2/
• Original model: https://huggingface.co/RTX3090x2/qwen2.5-7B-Instruct-v0.2.9-v0.3/

Name	Quant method	Size
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q2_K.gguf	Q2_K	2.81GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.IQ3_XS.gguf	IQ3_XS	3.12GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.IQ3_S.gguf	IQ3_S	3.26GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q3_K_S.gguf	Q3_K_S	3.25GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.IQ3_M.gguf	IQ3_M	3.33GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q3_K.gguf	Q3_K	3.55GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q3_K_M.gguf	Q3_K_M	3.55GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q3_K_L.gguf	Q3_K_L	3.81GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.IQ4_XS.gguf	IQ4_XS	3.96GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q4_0.gguf	Q4_0	4.13GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.IQ4_NL.gguf	IQ4_NL	4.16GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q4_K_S.gguf	Q4_K_S	4.15GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q4_K.gguf	Q4_K	4.36GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q4_K_M.gguf	Q4_K_M	4.36GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q4_1.gguf	Q4_1	4.54GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q5_0.gguf	Q5_0	4.95GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q5_K_S.gguf	Q5_K_S	4.95GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q5_K.gguf	Q5_K	5.07GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q5_K_M.gguf	Q5_K_M	5.07GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q5_1.gguf	Q5_1	5.36GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q6_K.gguf	Q6_K	5.82GB
qwen2.5-7B-Instruct-v0.2.9-v0.3.Q8_0.gguf	Q8_0	7.54GB

Original model description:

base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit language:

• en license: apache-2.0 tags:
• text-generation-inference
• transformers
• unsloth
• qwen2
• trl

---

Uploaded model

• Developed by: RTX3090x2
• License: apache-2.0
• Finetuned from model : unsloth/qwen2.5-7b-instruct-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.