You can deploy this model and start earning money today!

RichardErkhov/
Diksha2001_-_VLLM-llama3.1-lora-16bit-V3-gguf

Name: Diksha2001_-_VLLM-llama3.1-lora-16bit-V3-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

VLLM-llama3.1-lora-16bit-V3 - GGUF

Name	Quant method	Size
VLLM-llama3.1-lora-16bit-V3.Q2_K.gguf	Q2_K	2.96GB
VLLM-llama3.1-lora-16bit-V3.IQ3_XS.gguf	IQ3_XS	3.28GB
VLLM-llama3.1-lora-16bit-V3.IQ3_S.gguf	IQ3_S	3.43GB
VLLM-llama3.1-lora-16bit-V3.Q3_K_S.gguf	Q3_K_S	3.41GB
VLLM-llama3.1-lora-16bit-V3.IQ3_M.gguf	IQ3_M	3.52GB
VLLM-llama3.1-lora-16bit-V3.Q3_K.gguf	Q3_K	3.74GB
VLLM-llama3.1-lora-16bit-V3.Q3_K_M.gguf	Q3_K_M	3.74GB
VLLM-llama3.1-lora-16bit-V3.Q3_K_L.gguf	Q3_K_L	4.03GB
VLLM-llama3.1-lora-16bit-V3.IQ4_XS.gguf	IQ4_XS	4.18GB
VLLM-llama3.1-lora-16bit-V3.Q4_0.gguf	Q4_0	4.34GB
VLLM-llama3.1-lora-16bit-V3.IQ4_NL.gguf	IQ4_NL	4.38GB
VLLM-llama3.1-lora-16bit-V3.Q4_K_S.gguf	Q4_K_S	4.37GB
VLLM-llama3.1-lora-16bit-V3.Q4_K.gguf	Q4_K	4.58GB
VLLM-llama3.1-lora-16bit-V3.Q4_K_M.gguf	Q4_K_M	4.58GB
VLLM-llama3.1-lora-16bit-V3.Q4_1.gguf	Q4_1	4.78GB
VLLM-llama3.1-lora-16bit-V3.Q5_0.gguf	Q5_0	5.21GB
VLLM-llama3.1-lora-16bit-V3.Q5_K_S.gguf	Q5_K_S	5.21GB
VLLM-llama3.1-lora-16bit-V3.Q5_K.gguf	Q5_K	5.34GB
VLLM-llama3.1-lora-16bit-V3.Q5_K_M.gguf	Q5_K_M	5.34GB
VLLM-llama3.1-lora-16bit-V3.Q5_1.gguf	Q5_1	5.65GB
VLLM-llama3.1-lora-16bit-V3.Q6_K.gguf	Q6_K	6.14GB
VLLM-llama3.1-lora-16bit-V3.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit tags:

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