You can deploy this model and start earning money today!

RichardErkhov/
Qurtana_-_Qwen-2.5-0.5B-MathInstruct.rev.2-gguf

Name: Qurtana_-_Qwen-2.5-0.5B-MathInstruct.rev.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Qwen-2.5-0.5B-MathInstruct.rev.2 - GGUF

Name	Quant method	Size
Qwen-2.5-0.5B-MathInstruct.rev.2.Q2_K.gguf	Q2_K	0.39GB
Qwen-2.5-0.5B-MathInstruct.rev.2.IQ3_XS.gguf	IQ3_XS	0.39GB
Qwen-2.5-0.5B-MathInstruct.rev.2.IQ3_S.gguf	IQ3_S	0.39GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q3_K_S.gguf	Q3_K_S	0.39GB
Qwen-2.5-0.5B-MathInstruct.rev.2.IQ3_M.gguf	IQ3_M	0.39GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q3_K.gguf	Q3_K	0.4GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q3_K_M.gguf	Q3_K_M	0.4GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q3_K_L.gguf	Q3_K_L	0.42GB
Qwen-2.5-0.5B-MathInstruct.rev.2.IQ4_XS.gguf	IQ4_XS	0.4GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q4_0.gguf	Q4_0	0.4GB
Qwen-2.5-0.5B-MathInstruct.rev.2.IQ4_NL.gguf	IQ4_NL	0.4GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q4_K_S.gguf	Q4_K_S	0.45GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q4_K.gguf	Q4_K	0.46GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q4_K_M.gguf	Q4_K_M	0.46GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q4_1.gguf	Q4_1	0.43GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q5_0.gguf	Q5_0	0.46GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q5_K_S.gguf	Q5_K_S	0.48GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q5_K.gguf	Q5_K	0.49GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q5_K_M.gguf	Q5_K_M	0.49GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q5_1.gguf	Q5_1	0.49GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q6_K.gguf	Q6_K	0.61GB
Qwen-2.5-0.5B-MathInstruct.rev.2.Q8_0.gguf	Q8_0	0.63GB

Original model description:

base_model: unsloth/Qwen2.5-0.5B-Instruct language:

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