---

language:

• en

license: other license_name: llama3 model_name: Llama3 8B arxiv: 2307.09288 base_model: meta-llama/Meta-Llama-3-8B inference: false model_creator: Meta Llama3 model_type: llama pipeline_tag: text-generation quantized_by: Second State Inc.

---

---

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

Original Model

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

LoRA Adapter

FinGPT/fingpt-mtllama3-8b_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-Q2K.gguf | Q2K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
| FinGPT-MT-Llama-3-8B-LoRA-Q3KL.gguf | Q3K_L | 3 | 4.32 GB| small, substantial quality loss |
| FinGPT-MT-Llama-3-8B-LoRA-Q3KM.gguf | Q3K_M | 3 | 4.02 GB| very small, high quality loss |
| FinGPT-MT-Llama-3-8B-LoRA-Q3KS.gguf | Q3K_S | 3 | 3.66 GB| very small, high quality loss |
| FinGPT-MT-Llama-3-8B-LoRA-Q40.gguf | Q40 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3KM |
| FinGPT-MT-Llama-3-8B-LoRA-Q4KM.gguf | Q4K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
| FinGPT-MT-Llama-3-8B-LoRA-Q4KS.gguf | Q4K_S | 4 | 4.69 GB| small, greater quality loss |
| FinGPT-MT-Llama-3-8B-LoRA-Q50.gguf | Q50 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4KM |
| FinGPT-MT-Llama-3-8B-LoRA-Q5KM.gguf | Q5K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
| FinGPT-MT-Llama-3-8B-LoRA-Q5KS.gguf | Q5K_S | 5 | 5.6 GB| large, low quality loss - recommended |
| FinGPT-MT-Llama-3-8B-LoRA-Q6K.gguf | Q6K | 6 | 6.6 GB| very large, extremely low quality loss |
| FinGPT-MT-Llama-3-8B-LoRA-Q80.gguf | Q80 | 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.