You can deploy this model and start earning money today!

RichardErkhov/
quocdat25_-_vLLM-fast-apply-16bit-v0.1-gguf

Name: quocdat25_-_vLLM-fast-apply-16bit-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

vLLM-fast-apply-16bit-v0.1 - GGUF

Name	Quant method	Size
vLLM-fast-apply-16bit-v0.1.Q2_K.gguf	Q2_K	2.81GB
vLLM-fast-apply-16bit-v0.1.IQ3_XS.gguf	IQ3_XS	3.12GB
vLLM-fast-apply-16bit-v0.1.IQ3_S.gguf	IQ3_S	3.26GB
vLLM-fast-apply-16bit-v0.1.Q3_K_S.gguf	Q3_K_S	3.25GB
vLLM-fast-apply-16bit-v0.1.IQ3_M.gguf	IQ3_M	3.33GB
vLLM-fast-apply-16bit-v0.1.Q3_K.gguf	Q3_K	3.55GB
vLLM-fast-apply-16bit-v0.1.Q3_K_M.gguf	Q3_K_M	3.55GB
vLLM-fast-apply-16bit-v0.1.Q3_K_L.gguf	Q3_K_L	3.81GB
vLLM-fast-apply-16bit-v0.1.IQ4_XS.gguf	IQ4_XS	3.96GB
vLLM-fast-apply-16bit-v0.1.Q4_0.gguf	Q4_0	4.13GB
vLLM-fast-apply-16bit-v0.1.IQ4_NL.gguf	IQ4_NL	4.16GB
vLLM-fast-apply-16bit-v0.1.Q4_K_S.gguf	Q4_K_S	4.15GB
vLLM-fast-apply-16bit-v0.1.Q4_K.gguf	Q4_K	4.36GB
vLLM-fast-apply-16bit-v0.1.Q4_K_M.gguf	Q4_K_M	4.36GB
vLLM-fast-apply-16bit-v0.1.Q4_1.gguf	Q4_1	4.54GB
vLLM-fast-apply-16bit-v0.1.Q5_0.gguf	Q5_0	4.95GB
vLLM-fast-apply-16bit-v0.1.Q5_K_S.gguf	Q5_K_S	4.95GB
vLLM-fast-apply-16bit-v0.1.Q5_K.gguf	Q5_K	5.07GB
vLLM-fast-apply-16bit-v0.1.Q5_K_M.gguf	Q5_K_M	5.07GB
vLLM-fast-apply-16bit-v0.1.Q5_1.gguf	Q5_1	5.36GB
vLLM-fast-apply-16bit-v0.1.Q6_K.gguf	Q6_K	5.82GB
vLLM-fast-apply-16bit-v0.1.Q8_0.gguf	Q8_0	7.54GB

Original model description:

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

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