voyage-4-nano
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve MongoDB/voyage-4-nanoNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
voyage-4-nano is an open-weight text embedding model from MongoDB, published on Hugging Face in January 2026. It has 350M parameters and is released under the apache-2.0 license.
HardwareLink to this section
At full FP16 precision the weights need about 1 GB of memory; 8-bit quantization brings that to roughly 1 GB. That is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs.
PopularityLink to this section
voyage-4-nano had 90,118 downloads on Hugging Face in the last month and has 152 likes.
Run it locallyLink to this section
The weights are on Hugging Face and load with sentence-transformers. Follow the model card for the exact setup and license terms.
Frequently asked
Quick answers to common questions
How much VRAM does voyage-4-nano need?
voyage-4-nano with 0.35B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is voyage-4-nano better than other MongoDB models?
voyage-4-nano has 0.35B parameters with 40,960 context - a strong choice for embeddings.
What license is voyage-4-nano under?
voyage-4-nano is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs voyage-4-nano well?
With 0.35B parameters, voyage-4-nano requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for voyage-4-nano?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can voyage-4-nano's context window handle?
voyage-4-nano supports a 40,960-token context window - enough for most medium-length documents and conversations. Real-world usable context may vary by implementation.
What models compete with voyage-4-nano?
voyage-4-nano competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec