---

FinGPT-MT-Llama-3-8B-LoRA-GGUF

Original Model

meta-llama/Meta-Llama-3-8B

LoRA Adapter

FinGPT/fingpt-mt_llama3-8b_lora

Run with LlamaEdge

• LlamaEdge version: coming soon

• Context size: 8192

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf	Q2_K	2	3.18 GB	smallest, significant quality loss - not recommended for most purposes
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf	Q3_K_L	3	4.32 GB	small, substantial quality loss
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf	Q3_K_M	3	4.02 GB	very small, high quality loss
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf	Q3_K_S	3	3.66 GB	very small, high quality loss
FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf	Q4_0	4	4.66 GB	legacy; small, very high quality loss - prefer using Q3_K_M
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf	Q4_K_M	4	4.92 GB	medium, balanced quality - recommended
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf	Q4_K_S	4	4.69 GB	small, greater quality loss
FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf	Q5_0	5	5.6 GB	legacy; medium, balanced quality - prefer using Q4_K_M
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf	Q5_K_M	5	5.73 GB	large, very low quality loss - recommended
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf	Q5_K_S	5	5.6 GB	large, low quality loss - recommended
FinGPT-MT-Llama-3-8B-LoRA-Q6_K.gguf	Q6_K	6	6.6 GB	very large, extremely low quality loss
FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf	Q8_0	8	8.54 GB	very large, extremely low quality loss - not recommended
FinGPT-MT-Llama-3-8B-LoRA-f16.gguf	f16	16	16.1 GB

Quantized with llama.cpp b3807.