Llama 3.3 70B Instruct (Q4_K_M)
Meta · 70.6B · q4_k_m
Specs verified:
Specifications
- Publisher
- Meta
Source
- Retrieved
- Last verified
- Verification
- Verified
- Parameters
- 70.6B
Source
- Retrieved
- Last verified
- Verification
- Verified
- Quantization
- q4_k_m
Source
- Retrieved
- Last verified
- Verification
- Verified
- Minimum VRAM
- 42.5 GB
Source
- Retrieved
- Last verified
- Verification
- Unverified
- Context length
- 128K tokens
Source
- Retrieved
- Last verified
- Verification
- Verified
- Modality
- text
Source
- Retrieved
- Last verified
- Verification
- Verified
- License
- Llama 3.3 Community License
Source
- Retrieved
- Last verified
- Verification
- Verified
Graphics cards that can run it
No graphics cards recorded that can run this model.
Benchmarks
No benchmark results recorded.
Sources
- github.com (external site) · verified
- Publisher
- Modality
- License
- huggingface.co (external site) · verified
- Parameters
- huggingface.co (external site) · verified
- Quantization
- Minimum VRAM
- huggingface.co (external site) · verified
- Context length