QwenQwen3.5-397B (MoE) on AMD Radeon RX 9060 XT 8GB
AMD Radeon RX 9060 XT 8GB cannot run Qwen3.5-397B (MoE). 8 GB VRAM is insufficient at any quantization level.
Model Size
397B
Device VRAM
8 GB
Bandwidth
256 GB/s
Quantization
Q2_K
Performance by Quantization
OwnRig currently has one published compatibility entry for Qwen3.5-397B (MoE) on AMD Radeon RX 9060 XT 8GB at Q2_K. This pairing has limitations — check the rating and notes below.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q2_K | – | – | ✗ Offload | Not viable | estimated |
Notes
Q2_K
RDNA 4 card with improving ROCm support; Vulkan remains the safer default in llama.cpp. Q2_K needs ~140.0GB and relies on offloading on this card. MoE models still have to load the full expert pool into memory. Does not fit in 8GB VRAM (140GB required for Q2_K).
About Qwen3.5-397B (MoE)
Qwen3.5-397B (MoE) (397B) is a chat, coding, ai coding, reasoning, multi-purpose model. Frontier-scale MoE with 397B total parameters and roughly 30B active per token. Requires an enormous memory footprint even when quantized, so local runs are limited to GB300-class hardware or aggressive offloading setups.
View all Qwen3.5-397B (MoE) hardware options →About AMD Radeon RX 9060 XT 8GB
AMD Radeon RX 9060 XT 8GB has 8 GB at 256 GB/s. Street price: $299.
See all models AMD Radeon RX 9060 XT 8GB can run →Estimate method: Estimated from rtx-4060-ti-16gb compatibility patterns plus ROCm/Vulkan adjustments. Reference hardware source: github.com (2026-05-26)
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.