Store › model › Embeddings

bge-m3-GGUF

Name: bge-m3-GGUF
Author: cstr

by cstr · source Hugging Face · updated 2026-08-02

mit581 MB~2 GB RAMsource aliveunlabeled

GGUF format of BAAI/bge-m3 for use with CrispEmbed.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:cstr/bge-m3-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/cstr/bge-m3-GGUF
License: mit
Requirements: about 2 GB of RAM, 581 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
Tags: gguf embeddings ggml text-embeddings xlm-r crispembed feature-extraction multilingual endpoints_compatible

Numbers

2,123 downloads on Hugging Face
1 likes
license mit
0.6 GB for bge-m3-q8_0.gguf
4,402,710 npm downloads a week for @huggingface/transformers
latest @huggingface/transformers@4.3.0

Numbers as of 2026-10-02 21:00 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`bge-m3-iq4_xs.gguf`	IQ4_XS	428 MB
`bge-m3-q4_k-imatrix.gguf`	Q4_K	437 MB
`bge-m3-q4_k.gguf`	Q4_K	437 MB
`bge-m3-q8_0.gguf`	Q8_0	581 MB
`bge-m3.gguf`		2.1 GB

From the source README

bge-m3 GGUF

GGUF format of BAAI/bge-m3 for use with CrispEmbed.

BGE-M3. Dense + sparse + ColBERT multi-vector retrieval in one model. 100+ languages, 8192 context.

Files

| File | Quantization | Size |
|------|-------------|------|
| bge-m3-q4_k.gguf | Q4_K | 438 MB |
| bge-m3-q8_0.gguf | Q8_0 | 583 MB |
| bge-m3.gguf | F32 | 2175 MB |

Quick Start

# Download
huggingface-cli download cstr/bge-m3-GGUF bge-m3-q4_k.gguf --local-dir .

# Run with CrispEmbed
./crispembed -m bge-m3-q4_k.gguf "Hello world"

# Or with auto-download
./crispembed -m bge-m3 "Hello world"
```

Model Details

| Property | Value |
|----------|-------|
| Architecture | XLM-R |
| Parameters | 568M |
| Embedding Dimension | 1024 |
| Layers | 24 |
| Pooling | mean |
| Tokenizer | SentencePiece |
| Base Model | BAAI/bge-m3 |

Verification

Card id model:hf:cstr/bge-m3-GGUF · collected 2026-10-02 21:00 UTC · JSON