nomic-embed-text v1.5 on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs nomic-embed-text v1.5 excellently at FP16 — 2000 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
137M
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
FP16
Performance by Quantization
OwnRig currently has one published compatibility entry for nomic-embed-text v1.5 on NVIDIA Grace Blackwell Ultra GB300 at FP16. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| FP16 | 2000 tok/s | 3ms | ✓ Yes | Excellent | estimated |
Notes
FP16
Embedding model at full quality. 288GB headroom. Instant embeddings.
About nomic-embed-text v1.5
nomic-embed-text v1.5 (137M) is a embeddings, ai building model. High-quality text embedding model for RAG pipelines. 137M params, negligible VRAM. Competitive with OpenAI's ada-002 on MTEB benchmarks. Essential for builders running local RAG with Cursor or similar tools. Can run concurrently with coding models without meaningful VRAM impact.
View all nomic-embed-text v1.5 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.