Meta
Llama 3.3 70B
70,6B
Parameters
39,6 Go
Q4_K_M file
≥ 41,1 Go
Recommended VRAM
131 072
Max context
Not measured yet
No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.
Measure my card →Which cards should it fit on?
Cards on the site whose video memory covers the recommended 41,1 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.
Technical sheet
- Published
- 2024-11-26
- Architecture
- 80 layers · 8 KV heads · dimension 128
- Attention
- Standard: every layer keeps the whole context in memory.
- Context cache (f16)
- ≈ 313 MB per 1,000 tokens · 10,0 Go for 32,768 tokens
- GGUF file
- bartowski/Llama-3.3-70B-Instruct-GGUF · Llama-3.3-70B-Instruct-Q4_K_M.gguf Download (39,6 Go)
- Official repo
- meta-llama/Llama-3.3-70B-Instruct
Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.