GPUs & Macs › AMD Radeon Pro WX 4100
AMD Radeon Pro WX 4100: local LLM speed
Llama 2 7B (Q4_0) generates 16.6 tokens/s on the AMD Radeon Pro WX 4100 (Vulkan), and processes prompts at 76 tokens/s.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 2 7B | 16.6 | 76 | Q4_0 | Vulkan FA on | tg128 | llama.cpp #10879 details |
| Llama 2 7B | 16.1 | 79 | Q4_0 | Vulkan FA off | tg128 | llama.cpp #10879 details |
What fits on the AMD Radeon Pro WX 4100
Estimates for this chip are scaled from a measured run: Llama 2 7B Q4_0 at 16.6 tok/s (Vulkan, source). Fit assumes the whole model in GPU memory with ~8K context.
Memory size unknown for this device.
Similar hardware
AMD Radeon Pro W6800X Duo · AMD Radeon Pro W6800X · AMD Radeon Pro V540 · AMD Radeon Pro W5700 · AMD FirePro S9300 x2 · AMD Radeon Pro V340 · AMD Radeon RX 470 · AMD Radeon Pro W5500