Compare
Compare models side by side
Choose up to 4 models to see their file size, memory, license and third-party evaluations side by side.
Comparison table
| Item | Llama-4-Scout-17B-16E-Instruct meta-llama ✕ Remove |
|---|---|
| Parameters | 107.8B |
| Architecture | llama4 |
| Max context length | 10,485,760 |
| Representative quantization and size Measured | Q4_K_M · 65.4 GB |
| Memory at 8K Estimated | 67.9 GB |
| Memory at 32K Estimated | 69.2 GB |
| VRAM it fits (8K) Estimated | VRAM 64 GB+ |
| Smallest quantization (8K) Estimated | UD-TQ1_0 · 29.3 GB → 31.8 GB |
| License | Llama 4 Community License Conditional |
| llama.cpp support | llama.cpp b5074 and later |
| Downloads (30 days, total) | 40,867 |
| Human preference (LMArena) | 1,322 Llama 4 Scout 17B 16E Instruct |
| Capabilities (Epoch AI) | - |
| Hard science (GPQA) | 51.8% Llama-4-Scout-17B-16E-Instruct |
- The representative quantization is Q4_K_M (or the smallest one if missing) from the source with the most downloads. Memory is estimated with an f16 KV cache.
- Third-party evaluations are other organizations' values for the original model before quantization, not this site's rating (sources are on the ranking page).
- This site does not judge which model is better or give an overall score.