llama-3.3-70b-Instruct-4bit
1 workload result across 1 hardware configuration.
Fastest local config
16.8 decode tok/s
on M3 Ultra (60-core GPU) + 96GB unified via mlx — see full run
Local runs (1 run)
Runs from contributors' own machines via MLX, llama.cpp, vLLM, exllamav2, or ollama. Signed on the submitter's hardware.
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | 16.78tok/s | 25.09tok/s | 5,420ms | r_sx3a4y9n-m4 |