Skip to content

AMD Radeon RX 9060 XT 16GB

AMD · 16GB GDDR6 · Can run 49 models

Buy Amazon
Manufacturer AMD
VRAM 16 GB
Memory Type GDDR6
Architecture RDNA 4
Stream Procs 2,048
Bandwidth 538 GB/s
TDP 150W
MSRP $329
Released Jun 5, 2025

AI Notes

The RX 9060 XT 16GB brings 16GB of VRAM to the mid-range segment, enough to run 13B models comfortably and even attempt larger models with aggressive quantization. Its lower power draw makes it an efficient option for always-on inference. ROCm support for RDNA 4 is improving but may still require some setup effort compared to NVIDIA CUDA.

Compatible Models

Model Parameters Best Quant VRAM Used Fit Est. Speed
Qwen 3 0.6B 600M Q4_K_M 2.5 GB Runs ~215 tok/s
Gemma 3 1B 1B Q8_0 2 GB Runs ~269 tok/s
Llama 3.2 1B 1B Q8_0 3 GB Runs ~179 tok/s
DeepSeek R1 1.5B 1.5B Q8_0 3 GB Runs ~179 tok/s
Gemma 2 2B 2B Q8_0 4 GB Runs ~135 tok/s
Gemma 3n E2B 2B Q4_K_M 3.3 GB Runs ~163 tok/s
Llama 3.2 3B 3B Q8_0 5 GB Runs ~108 tok/s
Phi-3 Mini 3.8B 3.8B Q8_0 5.8 GB Runs ~93 tok/s
Phi-4 Mini 3.8B 3.8B Q4_K_M 4.5 GB Runs ~120 tok/s
Gemma 3 4B 4B Q4_K_M 5 GB Runs ~108 tok/s
Gemma 3n E4B 4B Q4_K_M 4.5 GB Runs ~120 tok/s
Qwen 3 4B 4B Q4_K_M 4.5 GB Runs ~120 tok/s
DeepSeek R1 7B 7B Q8_0 9 GB Runs ~60 tok/s
Falcon 3 7B 7B Q4_K_M 6.8 GB Runs ~79 tok/s
Mistral 7B 7B Q8_0 9 GB Runs ~60 tok/s
Qwen 2.5 7B 7B Q8_0 9 GB Runs ~60 tok/s
Qwen 2.5 Coder 7B 7B Q8_0 9 GB Runs ~60 tok/s
Qwen 2.5 VL 7B 7B Q4_K_M 7 GB Runs ~77 tok/s
Cogito 8B 8B Q4_K_M 7.5 GB Runs ~72 tok/s
DeepSeek R1 8B 8B Q4_K_M 7.5 GB Runs ~72 tok/s
Llama 3.1 8B 8B Q8_0 10 GB Runs ~54 tok/s
Nemotron 3 Nano 8B 8B Q4_K_M 7.5 GB Runs ~72 tok/s
Qwen 3 8B 8B Q4_K_M 7.5 GB Runs ~72 tok/s
Gemma 2 9B 9B Q8_0 11 GB Runs ~49 tok/s
Falcon 3 10B 10B Q4_K_M 8.5 GB Runs ~63 tok/s
Llama 3.2 Vision 11B 11B Q4_K_M 8.5 GB Runs ~63 tok/s
Gemma 3 12B 12B Q4_K_M 10.5 GB Runs ~51 tok/s
Mistral Nemo 12B 12B Q4_K_M 9.5 GB Runs ~57 tok/s
DeepSeek R1 14B 14B Q4_K_M 9.9 GB Runs ~54 tok/s
Phi-4 14B 14B Q4_K_M 9.9 GB Runs ~54 tok/s
Phi-4 Reasoning 14B 14B Q4_K_M 11 GB Runs ~49 tok/s
Qwen 2.5 14B 14B Q4_K_M 9.9 GB Runs ~54 tok/s
Qwen 2.5 Coder 14B 14B Q4_K_M 12 GB Runs ~45 tok/s
Qwen 3 14B 14B Q4_K_M 12 GB Runs ~45 tok/s
Codestral 22B 22B Q4_K_M 14.7 GB Runs (tight) ~37 tok/s
StarCoder2 15B 15B Q8_0 17 GB CPU Offload ~10 tok/s
Devstral 24B 24B Q4_K_M 17 GB CPU Offload ~10 tok/s
Magistral Small 24B 24B Q4_K_M 17 GB CPU Offload ~10 tok/s
Mistral Small 3.1 24B 24B Q4_K_M 18 GB CPU Offload ~9 tok/s
Gemma 2 27B 27B Q4_K_M 17.7 GB CPU Offload ~9 tok/s
Gemma 3 27B 27B Q4_K_M 20 GB CPU Offload ~8 tok/s
Qwen 3 30B-A3B (MoE) 30B Q4_K_M 22 GB CPU Offload ~7 tok/s
Cogito 32B 32B Q4_K_M 21.5 GB CPU Offload ~8 tok/s
DeepSeek R1 32B 32B Q4_K_M 20.7 GB CPU Offload ~8 tok/s
Qwen 2.5 32B 32B Q4_K_M 20.7 GB CPU Offload ~8 tok/s
Qwen 2.5 Coder 32B 32B Q4_K_M 23 GB CPU Offload ~7 tok/s
Qwen 3 32B 32B Q4_K_M 23 GB CPU Offload ~7 tok/s
QwQ 32B 32B Q4_K_M 21.5 GB CPU Offload ~8 tok/s
Command R 35B 35B Q4_K_M 22.5 GB CPU Offload ~7 tok/s
20 model(s) are too large for this hardware.