GPUs & Macs › AMD Radeon RX 5500 XT
AMD Radeon RX 5500 XT: local LLM speed
1 measured result for the AMD Radeon RX 5500 XT.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | 56.2 | 174 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the AMD Radeon RX 5500 XT
Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.5-4B | IQ4_XS | 2.5 GB | – estimate |
| Qwen3-4B | Q4_K_M | 2.5 GB | – estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | – estimate |
| DeepSeek-R1-0528-Qwen3-8B | UD-IQ1_M | 2.4 GB | – estimate |
| Llama-3.2-3B-Instruct | Q5_K_M | 2.3 GB | – estimate |
| Phi-4-mini-instruct | Q4_K_M | 2.5 GB | – estimate |
| gemma-3-4b-it | Q4_K_M | 2.5 GB | – estimate |
| Qwen3.5-0.8B | Q8_0 | 0.8 GB | – estimate |
| Llama-3.2-3B-Instruct-uncensored | Q5_K_M | 2.6 GB | – estimate |
| Qwen3-0.6B | Q8_0 | 0.8 GB | – estimate |
| GLM-OCR | Q8_0 | 1.0 GB | – estimate |
| Qwen3-ASR-1.7B | Q8_0 | 2.2 GB | – estimate |
| SmolLM3-3B | Q4_K_M | 1.9 GB | – estimate |
| Nanbeige4.2-3B | Q4_K_S | 2.6 GB | – estimate |
Similar hardware
AMD Radeon RX 6500 XT · AMD Radeon Pro W6800X Duo · AMD Radeon Pro W6800X · AMD Radeon RX 5700 XT · AMD Radeon Pro V540 · AMD Radeon Pro W5700 · AMD Radeon RX Vega 64 · AMD Radeon RX 6650 XT