GPUs & Macs › AMD Radeon RX 6600M
AMD Radeon RX 6600M: local LLM speed
Llama 2 7B (Q4_0) generates 48.2 tokens/s on the AMD Radeon RX 6600M (Vulkan), and processes prompts at 606 tokens/s.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 2 7B | 48.2 | 606 | Q4_0 | Vulkan FA off | tg128 | llama.cpp #10879 details |
What fits on the AMD Radeon RX 6600M
Estimates for this chip are scaled from a measured run: Llama 2 7B Q4_0 at 48.2 tok/s (Vulkan, source). Fit assumes the whole model in GPU memory with ~8K context.
Memory size unknown for this device.
Similar hardware
AMD BC-250 · AMD Radeon RX 6800M · AMD Radeon RX 7600M XT · AMD Ryzen AI 300 Series · AMD Ryzen 6000 Series · AMD Ryzen 7000 Series · AMD Ryzen 8000 Series · AMD Ryzen Z1 Extreme