BGE Large EN v1.5 vs Nomic Embed Text v1.5

Side-by-side comparison of hardware requirements, quantization options, and specifications to help you choose the right model for your device.

Specifications Comparison

SpecBGE Large EN v1.5Nomic Embed Text v1.5
Parameters0.335B0.137B
Architecturebertnomic-bert
LicenseMITApache 2.0
Context Length1K tokens8K tokens
CategoryEmbeddingEmbedding
AuthorBAAINomic AI
HF Downloads7.9M10.9M
VRAM Range0.83 - 1.12 GB0.3 - 0.76 GB
Quantizations2 options2 options
Best Quality Score100%100%

Quantization Options

BGE Large EN v1.5

Q8_0
0.3 GB0.83 GB VRAM98% quality
FP16
0.6 GB1.12 GB VRAM100% quality

Nomic Embed Text v1.5

Q8_0
0.1 GB0.3 GB VRAM98% quality
FP16
0.3 GB0.76 GB VRAM100% quality

Which Should You Choose?

Nomic Embed Text v1.5 is more memory-efficient, starting at just 0.3GB VRAM compared to 0.83GB for BGE Large EN v1.5. BGE Large EN v1.5 is significantly larger at 0.335B parameters, which generally means better output quality but requires more hardware.

Related Comparisons