DeepSeekDeepSeek R1 on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 handles DeepSeek R1 well at Q4_K_M — 20 tok/s. Solid daily-driver performance on 288 GB VRAM.
Model Size
671B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for DeepSeek R1 on NVIDIA Grace Blackwell Ultra GB300 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 | 20 tok/s | 350ms | ✓ Yes | Good | estimated |
Notes
Q4_K_M
671B MoE reasoning model at Q4_K_M (180GB). 108GB headroom. Only datacenter-class hardware can run this without offloading.
About DeepSeek R1
DeepSeek R1 (671B) is a reasoning, coding, ai coding, multi-purpose model. DeepSeek's reasoning-focused model. Same MoE architecture as V3 (671B total, ~37B active per token). Excels at chain-of-thought reasoning, math, and complex code. Requires the same massive hardware as V3: multi-GPU or 128GB+ Apple Silicon at heavy quantization. For most home users, the distilled versions (7B, 32B) are more practical.
View all DeepSeek R1 hardware options →About NVIDIA Grace Blackwell Ultra GB300
NVIDIA Grace Blackwell Ultra GB300 has 288 GB at 8000 GB/s. Street price: $30,000.
See all models NVIDIA Grace Blackwell Ultra GB300 can run →Estimate method: Estimated from GB300 bandwidth ratio vs RTX 4090. Reference hardware source: dell.com (2026-03-23)
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.