QwenQwen 2.5 14B Instruct on AMD Radeon RX 9070
Yes — AMD Radeon RX 9070 handles Qwen 2.5 14B Instruct well at Q4_K_M — 52 tok/s. Solid daily-driver performance on 16 GB VRAM.
Model Size
14.77B
Device VRAM
16 GB
Bandwidth
640 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Qwen 2.5 14B Instruct on AMD Radeon RX 9070 at Q4_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q4_K_M | 52 tok/s | 137ms | ✓ Yes | Good | estimated |
Notes
Q4_K_M
RDNA 4 card with improving ROCm support; Vulkan remains the safer default in llama.cpp. Q4_K_M fits in VRAM on this card.
About Qwen 2.5 14B Instruct
Qwen 2.5 14B Instruct (14.77B) is a chat, coding, reasoning, multi-purpose model. Capable general-purpose model with balanced coding and reasoning.
View all Qwen 2.5 14B Instruct hardware options →About AMD Radeon RX 9070
AMD Radeon RX 9070 has 16 GB at 640 GB/s. Street price: $549.
See all models AMD Radeon RX 9070 can run →Estimate method: Estimated from rtx-4060-ti-16gb compatibility patterns plus ROCm/Vulkan adjustments. Reference hardware source: github.com (2026-04-18)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.