cstr/gte-modernbert-base-GGUF

gte-modernbert-base GGUF

GGUF format of Alibaba-NLP/gte-modernbert-base for use with CrispEmbed.

Alibaba GTE ModernBERT Base. General-purpose English text embedding model with long context support (8,192 tokens). Strong MTEB performance (64.38) and long-document retrieval (LoCo 88.88).

Model details

• Architecture: ModernBERT encoder-only transformer (149M params)
• Embedding dimension: 768
• Languages: English
• Context length: 8,192 tokens
• MTEB score: 64.38
• License: Apache 2.0

Files

File	Quantization	Size
gte-modernbert-base.gguf	F32	~560 MB
gte-modernbert-base-q8_0.gguf	Q8_0	~150 MB
gte-modernbert-base-q4_k.gguf	Q4_K	~85 MB

Quick Start

See CrispEmbed for full documentation and CrispASR for speech-to-text.

Provenance and EU AI Act Art. 53 note

• Upstream model: Alibaba-NLP/gte-modernbert-base — published by Alibaba-NLP.
• Upstream licence: apache-2.0. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF/GGML). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.