Model reference · open weights
glove-quantized is an open-weight embedding model from NeuML. glove-6B-quantized (INT4) weighs 4 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the NeuML/glove-6B-quantized model card, 2026-10-01
What it is
| Released by | NeuML |
|---|---|
| Released | 2025-01-26 |
| Parameters | 4M |
| VRAM | 4 MB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This model is an export of these GloVe-6B English Vectors (300d) for staticvectors. staticvectors enables running inference in Python with NumPy. This helps it maintain solid runtime performance.
This model is a quantized version of the base model. It's using 10x256 Product Quantization.
from staticvectors import StaticVectors
model = StaticVectors("neuml/glove-6B-quantized")
model.embeddings(["word"])
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works