cl-nagoya / sentence-similarity updated 1 year ago

ruri-v3-310m

Name: ruri-v3-310m
Author: cl-nagoya

Ruri v3 is a general-purpose Japanese text embedding model built on top of ModernBERT-Ja. Ruri v3 offers several key technical advantages: - State-of-the-art performance for Japanese text embedding tasks. - Supports sequence lengths up to 8192 tokens - Previous versions of Ruri (v1, v2) were limited to 512. - Expanded vocabulary of 100K tokens, compared to 32K in v1 and v2 - The larger vocabulary make input sequences...

Params

310 M

Context

8,192

Downloads 30d

695 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

760 K692 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.3 GB	1.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: ModernBertModel
Parameters: 310 M
Tensor type: F32
Context length: 8,192
Vocabulary: 102,400
Layers / heads: 25 / 12
Licence: apache-2.0
First seen on the Hub: 2025-04-09
Training datasets: cl-nagoya/ruri-v3-dataset-ft
Added to our catalog: 2026-07-28

Compare with

all-MiniLM-L6-v2 257.8 M paraphrase-multilingual-MiniLM-L12-v2 59.4 M bge-m3 35.0 M all-mpnet-base-v2 25.2 M nomic-embed-text-v1.5 15.7 M paraphrase-multilingual-mpnet-base-v2 11.5 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB