GPUs & Macs › AMD Radeon RX 7900 XT
AMD Radeon RX 7900 XT: local LLM speed
Llama 2 7B (Q4_0) generates 123 tokens/s on the AMD Radeon RX 7900 XT (Vulkan), and processes prompts at 2,942 tokens/s.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Llama 2 7B | 123 | 2,942 | Q4_0 | Vulkan FA off | tg128 | llama.cpp #10879 details |
| Llama 2 7B | 121 | 2,701 | Q4_0 | Vulkan FA on | tg128 | llama.cpp #10879 details |
| Llama 2 7B | 116 | 3,098 | Q4_0 | ROCm FA off | tg128 | llama.cpp #15021 details |
| Llama 2 7B | 112 | 3,262 | Q4_0 | ROCm FA on | tg128 | llama.cpp #15021 details |
| gpt-oss 20B | 102 | 4,252 | BF16 | ROCm,RPC FA on | tg128 | llama.cpp #15396 details |
| Llama 3.2 1B Instruct | 99.2 | 4,957 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the AMD Radeon RX 7900 XT
Estimates for this chip are scaled from a measured run: Llama 2 7B Q4_0 at 123 tok/s (Vulkan, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | UD-Q4_K_M | 16.5 GB | 28.6 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 37.2 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 49.4 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 105 estimate |
| Qwen3.6-35B-A3B | UD-IQ4_XS | 17.7 GB | 155 estimate |
| gemma-4-26B-A4B-it | UD-Q4_K_M | 16.9 GB | 90.3 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 49.3 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 57.5 estimate |
| Muse-Glimmer-30B | UD-IQ3_M | 14.1 GB | 33.3 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 110 estimate |
| gemma-4-31B-it | Q4_K_S | 17.4 GB | 27.1 estimate |
| gemma-4-26B-A4B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 14.2 GB | 107 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 70.1 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 392 estimate |
Similar hardware
AMD Radeon RX 7900 XTX · AMD Radeon RX 9070 XT · AMD Radeon RX 9070 · AMD Radeon RX 7800 XT · AMD Radeon RX 7900 GRE · AMD Radeon RX 6900 XT · AMD Radeon RX 6800 · AMD Radeon VII