GoogleGemma 4 31B on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs Gemma 4 31B excellently at Q8_0 — 183 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
30.7B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q8_0
Performance by Quantization
OwnRig currently has one published compatibility entry for Gemma 4 31B on NVIDIA Grace Blackwell Ultra GB300 at Q8_0. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 183 tok/s | 50ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
30.7B model. Q8_0 32.64GB on 288GB discrete_gpu.
About Gemma 4 31B
Gemma 4 31B (30.7B) is a chat, coding, reasoning, multi-purpose model. Google's flagship open-weight model. Dense 30.7B parameters with 256K context. Benchmarks: 89.2% AIME 2026, 85.2% MMLU Pro, 84.3% GPQA Diamond, 80.0% LiveCodeBench v6, 86.4% agentic tool use. Supports text, image, and video input. Fits on a single RTX 4090 at Q4 or dual 16 GB GPUs. Direct successor to Gemma 3 27B with substantially better reasoning. Apache 2.0 licensed.
View all Gemma 4 31B 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 model architecture, quantization size, and device bandwidth. Reference hardware source: huggingface.co (2026-04-04)
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.