You can deploy this model and start earning money today!

RichardErkhov/
vlada22_-_Meta-Llama-3.1-8B-Instruct-finki-edu-5c-gguf

Name: vlada22_-_Meta-Llama-3.1-8B-Instruct-finki-edu-5c-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Meta-Llama-3.1-8B-Instruct-finki-edu-5c - GGUF

Name	Quant method	Size
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q2_K.gguf	Q2_K	2.96GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q3_K_S.gguf	Q3_K_S	3.41GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q3_K.gguf	Q3_K	3.74GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q3_K_M.gguf	Q3_K_M	3.74GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q3_K_L.gguf	Q3_K_L	2.54GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.IQ4_XS.gguf	IQ4_XS	4.18GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q4_0.gguf	Q4_0	4.34GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.IQ4_NL.gguf	IQ4_NL	4.38GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q4_K_S.gguf	Q4_K_S	4.37GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q4_K.gguf	Q4_K	4.58GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q4_K_M.gguf	Q4_K_M	4.58GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q4_1.gguf	Q4_1	4.78GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q5_0.gguf	Q5_0	5.21GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q5_K_S.gguf	Q5_K_S	5.21GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q5_K.gguf	Q5_K	5.34GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q5_K_M.gguf	Q5_K_M	5.34GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q5_1.gguf	Q5_1	5.65GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q6_K.gguf	Q6_K	6.14GB
Meta-Llama-3.1-8B-Instruct-finki-edu-5c.Q8_0.gguf	Q8_0	7.95GB

Original model description:

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

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