You can deploy this model and start earning money today!

RichardErkhov/
dat-lequoc_-_vLLM-fast-apply-16bit-v0.10.2-1.5B-gguf

Name: dat-lequoc_-_vLLM-fast-apply-16bit-v0.10.2-1.5B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

vLLM-fast-apply-16bit-v0.10.2-1.5B - GGUF

Name	Quant method	Size
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q2_K.gguf	Q2_K	0.63GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q3_K_S.gguf	Q3_K_S	0.71GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q3_K.gguf	Q3_K	0.77GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q3_K_M.gguf	Q3_K_M	0.77GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q3_K_L.gguf	Q3_K_L	0.82GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.IQ4_XS.gguf	IQ4_XS	0.84GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q4_0.gguf	Q4_0	0.87GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.IQ4_NL.gguf	IQ4_NL	0.88GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q4_K_S.gguf	Q4_K_S	0.88GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q4_K.gguf	Q4_K	0.92GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q4_K_M.gguf	Q4_K_M	0.92GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q4_1.gguf	Q4_1	0.95GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q5_0.gguf	Q5_0	1.02GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q5_K_S.gguf	Q5_K_S	1.02GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q5_K.gguf	Q5_K	1.05GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q5_K_M.gguf	Q5_K_M	1.05GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q5_1.gguf	Q5_1	1.1GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q6_K.gguf	Q6_K	1.19GB
vLLM-fast-apply-16bit-v0.10.2-1.5B.Q8_0.gguf	Q8_0	1.53GB

Original model description:

base_model: unsloth/Qwen2.5-Coder-1.5B language:

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