Store › model › Embeddings
multilingual-e5-small-GGUF
by cstr · source Hugging Face · updated 2026-08-04
mit126 MB~1 GB RAMsource aliveunlabeled
GGUF format of intfloat/multilingual-e5-small for use with CrispEmbed and Ollama.
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/multilingual-e5-small-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/cstr/multilingual-e5-small-GGUF
- License: mit
- Requirements: about 1 GB of RAM, 126 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
ggufembeddingsggmltext-embeddingsbertcrispembedollamafeature-extractionendefreszhjakoar
Numbers
- 2,303 downloads on Hugging Face
- 1 likes
- license mit
- 0.1 GB for multilingual-e5-small-q8_0.gguf
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
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 |
|---|---|---|
multilingual-e5-small-iq4_xs.gguf | IQ4_XS | 115 MB |
multilingual-e5-small-q4_k-imatrix.gguf | Q4_K | 115 MB |
multilingual-e5-small-q4_k.gguf | Q4_K | 115 MB |
multilingual-e5-small-q8_0.gguf | Q8_0 | 126 MB |
multilingual-e5-small.gguf | 455 MB |
From the source README
multilingual-e5-small GGUF
GGUF format of intfloat/multilingual-e5-small for use with CrispEmbed and Ollama.
Files
| File | Quantization | Size | cos vs HF |
|------|-------------|------|-----------|
| multilingual-e5-small.gguf | F32 | 455 MiB | 1.0000 (reference) |
| multilingual-e5-small-q8_0.gguf | Q8_0 | 126 MiB | 0.9999 |
| multilingual-e5-small-q4_k.gguf | Q4_K | 115 MiB | 0.990 |
| multilingual-e5-small-q4_k-imatrix.gguf | Q4_K + imatrix | 115 MiB | not measured |
| multilingual-e5-small-iq4_xs.gguf | IQ4_XS | 115 MiB | not measured |
Sizes are MiB (what the file browser above reports). Auxiliary files:
`multilingual-e5-small.imatrix`
(131 KiB, the importance matrix used for the imatrix/IQ quants) and
`multilingual-e5-small-imatrix-ab.txt`
(the A/B notes from producing it).
Recommended: Q8_0. It is within 0.0001 cosine of the F32 reference while
being 3.6× smaller, so F32 buys nothing you can measure. Drop to a 4-bit quant
only when you are memory-bound: they save a further 11 MiB — about 9% — and
Q4_K gives up an order of magnitude more accura…
Source: https://huggingface.co/cstr/multilingual-e5-small-GGUF
Card id model:hf:cstr/multilingual-e5-small-GGUF · collected 2026-10-02 21:00 UTC · JSON