← Back to Models
Meta Llama 3
Llama 3 is a family of large language models (LLMs) from Meta, designed for a wide array of applications and demonstrating state-of-the-art performance on various industry benchmarks.
meta-llama-3-8b
8B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:8bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| FP16 | 16 GB | 16 GB |
meta-llama-3-8b-instruct
8B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:8b-instructResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| FP16 | 16 GB | 16 GB |
meta-llama-3-8b-instruct-4bit
8B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:8b-instruct-4bitResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| 4-bit | 4-6 GB | 4-6 GB |
meta-llama-3-70b
70B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:70bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| FP16 | 140 GB | 140 GB |
meta-llama-3-70b-instruct
70B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:70b-instructResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| FP16 | 140 GB | 140 GB |
meta-llama-3-70b-instruct-4bit
70B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull meta-llama-3:70b-instruct-4bitResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| 4-bit | 35-40 GB | 35-40 GB |