meta-llama
Community-submitted & scraped throughput measurements. Sortable by generation speed.
← Back to model| Rig / GPU | Quant | Runtime | Context | Prompt tok/s | Gen tok/s | VRAM (GB) | Source | Reporter |
|---|---|---|---|---|---|---|---|---|
| Apple M3 Ultra (512 GB) | GGUF · Q4_K_M | llama.cpp | 2,048 | 162.30 | 14.41 | — | scraped | anonymous |
selected to compare · pick at least 2