You can deploy this model and start earning money today!

RichardErkhov/
dat-lequoc_-_vLLM-fast-apply-16bit-v0.12-Llama3.2-1B-gguf

Name: dat-lequoc_-_vLLM-fast-apply-16bit-v0.12-Llama3.2-1B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

vLLM-fast-apply-16bit-v0.12-Llama3.2-1B - GGUF

Name	Quant method	Size
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q2_K.gguf	Q2_K	0.54GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.IQ3_XS.gguf	IQ3_XS	0.58GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.IQ3_S.gguf	IQ3_S	0.6GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q3_K_S.gguf	Q3_K_S	0.6GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.IQ3_M.gguf	IQ3_M	0.61GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q3_K.gguf	Q3_K	0.64GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q3_K_M.gguf	Q3_K_M	0.64GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q3_K_L.gguf	Q3_K_L	0.68GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.IQ4_XS.gguf	IQ4_XS	0.7GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q4_0.gguf	Q4_0	0.72GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.IQ4_NL.gguf	IQ4_NL	0.72GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q4_K_S.gguf	Q4_K_S	0.72GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q4_K.gguf	Q4_K	0.75GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q4_K_M.gguf	Q4_K_M	0.75GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q4_1.gguf	Q4_1	0.77GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q5_0.gguf	Q5_0	0.83GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q5_K_S.gguf	Q5_K_S	0.83GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q5_K.gguf	Q5_K	0.85GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q5_K_M.gguf	Q5_K_M	0.85GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q5_1.gguf	Q5_1	0.89GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q6_K.gguf	Q6_K	0.95GB
vLLM-fast-apply-16bit-v0.12-Llama3.2-1B.Q8_0.gguf	Q8_0	1.23GB

Original model description:

base_model: unsloth/Llama-3.2-1B-Instruct-bnb-4bit language:

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