community pool / model answer
Meta-Llama-3-8B-Instruct
chat · meta-llama/Meta-Llama-3-8B-Instruct
48.4 tok/s · model median · 31 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B60 24GB | 4-bit | 43.1 tok/s | measured | 1,117 | - GB | 4,096 | llama.cpp |
| Arc Pro B60 24GB ×2 | 4-bit | 46.7 tok/s | measured | 874 | - GB | 4,096 | llama.cpp |
| RTX 5080 16GB | 4-bit | 129.5 tok/s | measured | 79 | - GB | 4,096 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.