GPUs & Macs › AMD Radeon 780M
AMD Radeon 780M: local LLM speed
4 measured results for the AMD Radeon 780M.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| gpt-oss 120B | 19.4 | 219 | MXFP4 | ROCm FA on | tg16 | llama.cpp #15396 details |
| Llama 3.2 1B Instruct | 11.0 | 582 | Q4_K_M | llamafile | LocalScore avg · n=10 | LocalScore LocalScore LocalScore LocalScore LocalScore LocalScore LocalScore LocalScore LocalScore LocalScore details |
| Llama 3.1 8B Instruct | 3.5 | 110 | Q4_K_M | llamafile | LocalScore avg · n=5 | LocalScore LocalScore LocalScore LocalScore LocalScore details |
| Qwen2.5 14B Instruct | 2.5 | 78 | Q4_K_M | llamafile | LocalScore avg · n=2 | LocalScore LocalScore details |
What fits on the AMD Radeon 780M
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 2.5 tok/s (llamafile, 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 6600M · AMD Radeon RX 7600M XT · AMD Ryzen AI 300 Series · AMD Ryzen 6000 Series · AMD Ryzen 7000 Series · AMD Ryzen 8000 Series