DeepSeekDeepSeek R1 Distill Qwen 32B on AMD Radeon RX 9070
AMD Radeon RX 9070 cannot run DeepSeek R1 Distill Qwen 32B. 16 GB VRAM is insufficient at any quantization level.
Model Size
32.5B
Device VRAM
16 GB
Bandwidth
640 GB/s
Quantization
Q3_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for DeepSeek R1 Distill Qwen 32B on AMD Radeon RX 9070 at Q3_K_M. This pairing has limitations — check the rating and notes below.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q3_K_M | 8 tok/s | 824ms | ✗ Offload | Marginal | estimated |
Notes
Q3_K_M
RDNA 4 card with improving ROCm support; Vulkan remains the safer default in llama.cpp. Q3_K_M needs ~15.5GB and relies on offloading on this card.
About DeepSeek R1 Distill Qwen 32B
DeepSeek R1 Distill Qwen 32B (32.5B) is a reasoning, coding, chat model. Distilled reasoning model with capable coding and chat performance.
View all DeepSeek R1 Distill Qwen 32B 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-4070-ti-super 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.