Nemotron 3 Embed 8B
Nemotron 3 Embed 8B is NVIDIA's embedding model. An 8-billion-parameter text embedding model producing high-dimensional vectors with matryoshka support for truncation, suited for retrieval and semantic search tasks.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video·
Embedding✓
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host Nemotron 3 Embed 8B, ranked by cheapest on-demand price. The model needs about 19 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g2-standard-4 |  GCP | nvidia-l4 | 24 GB | $0.705/hr | ||
| g6.xlarge |  AWS | L4 | 22 GB | $0.805/hr | ||
| g2-standard-8 | GCP | nvidia-l4 | 24 GB | $0.851/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Ministral 3 14B Instruct | 256K | $0.200 | $0.200 | Available | |
| Ministral 3 3B Instruct | 256K | $0.100 | $0.100 | Available | |
| Ministral 3 8B Instruct | 256K | $0.150 | $0.150 | Available | |
| Nemotron 3 Embed 8B | — | — | — | — | Current |