You can deploy this model and start earning money today!

RichardErkhov/
famepram_-_qwen2.5-3b_lora_model-merged-gguf

Name: famepram_-_qwen2.5-3b_lora_model-merged-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

qwen2.5-3b_lora_model-merged - GGUF

Name	Quant method	Size
qwen2.5-3b_lora_model-merged.Q2_K.gguf	Q2_K	1.19GB
qwen2.5-3b_lora_model-merged.IQ3_XS.gguf	IQ3_XS	1.3GB
qwen2.5-3b_lora_model-merged.IQ3_S.gguf	IQ3_S	1.36GB
qwen2.5-3b_lora_model-merged.Q3_K_S.gguf	Q3_K_S	1.35GB
qwen2.5-3b_lora_model-merged.IQ3_M.gguf	IQ3_M	1.39GB
qwen2.5-3b_lora_model-merged.Q3_K.gguf	Q3_K	1.48GB
qwen2.5-3b_lora_model-merged.Q3_K_M.gguf	Q3_K_M	1.48GB
qwen2.5-3b_lora_model-merged.Q3_K_L.gguf	Q3_K_L	1.59GB
qwen2.5-3b_lora_model-merged.IQ4_XS.gguf	IQ4_XS	1.63GB
qwen2.5-3b_lora_model-merged.Q4_0.gguf	Q4_0	1.7GB
qwen2.5-3b_lora_model-merged.IQ4_NL.gguf	IQ4_NL	1.71GB
qwen2.5-3b_lora_model-merged.Q4_K_S.gguf	Q4_K_S	1.71GB
qwen2.5-3b_lora_model-merged.Q4_K.gguf	Q4_K	1.8GB
qwen2.5-3b_lora_model-merged.Q4_K_M.gguf	Q4_K_M	1.8GB
qwen2.5-3b_lora_model-merged.Q4_1.gguf	Q4_1	1.86GB
qwen2.5-3b_lora_model-merged.Q5_0.gguf	Q5_0	2.02GB
qwen2.5-3b_lora_model-merged.Q5_K_S.gguf	Q5_K_S	2.02GB
qwen2.5-3b_lora_model-merged.Q5_K.gguf	Q5_K	2.07GB
qwen2.5-3b_lora_model-merged.Q5_K_M.gguf	Q5_K_M	2.07GB
qwen2.5-3b_lora_model-merged.Q5_1.gguf	Q5_1	2.18GB
qwen2.5-3b_lora_model-merged.Q6_K.gguf	Q6_K	2.36GB
qwen2.5-3b_lora_model-merged.Q8_0.gguf	Q8_0	3.06GB

Original model description:

base_model: famepram/qwen2.5-3b_lora_model tags:

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