nomic-embed-text v1.5 on NVIDIA GeForce RTX 4090
Yes — RTX 4090 runs nomic-embed-text v1.5 excellently at FP16 — real-time capable. 24 GB VRAM with plenty of headroom.
Model Size
137M
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantization
FP16
Performance by Quantization
OwnRig currently has one published compatibility entry for nomic-embed-text v1.5 on NVIDIA GeForce RTX 4090 at FP16. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| FP16 | – | 8ms | ✓ Yes | Excellent | estimated |
Notes
FP16
Negligible VRAM footprint. The key enabler for local RAG pipelines in builder workflows.
Running alongside Qwen 2.5 Coder 32B Q4: total ~19GB, leaving 5GB free on 4090.
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 GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Estimate method: Model card. Reference hardware source: huggingface.co (2026-01-15)
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.