QwenQwen 2.5 72B Instruct on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs Qwen 2.5 72B Instruct excellently at Q4_K_M — 60 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
72.7B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q4_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Qwen 2.5 72B Instruct 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 | 60 tok/s | 130ms | ✓ Yes | Excellent | estimated |
Notes
Q4_K_M
Efficient quantization with 248GB headroom.
About Qwen 2.5 72B Instruct
Qwen 2.5 72B Instruct (72.7B) is a chat, coding, ai coding, reasoning, multi-purpose model. Top-tier 72B model, competitive with Llama 3.1 70B. Capable at coding and structured output. Requires 48 GB+ VRAM for usable quantizations.
View all Qwen 2.5 72B Instruct 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.