Sentence Transformers

all-MiniLM-L6-v2

Tiny embedding model. Only 23MB. Perfect for on-device search.

0.023B parametersbertapache-2.00K context0.1GB - 0.1GB VRAM

Check Your Hardware

See which quantizations of all-MiniLM-L6-v2 your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q8_080.023 GB0.1 GB0.2 GB
92%

Frequently Asked Questions

How much VRAM do I need to run all-MiniLM-L6-v2?

all-MiniLM-L6-v2 requires 0.1GB VRAM minimum with Q8_0 quantization. For full precision, you need 0.1GB VRAM.

What is the best quantization for all-MiniLM-L6-v2?

Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.