Store › model › Embeddings

E5-Mistral-7B-Instruct-Embedding-GGUF

Name: E5-Mistral-7B-Instruct-Embedding-GGUF
Author: second-state

by second-state · source Hugging Face · updated 2024-07-01

mit4.1 GB~6 GB RAMsource aliveunlabeled

embedding model by second-state, gguf files on Hugging Face.

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:second-state/E5-Mistral-7B-Instruct-Embedding-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/second-state/E5-Mistral-7B-Instruct-Embedding-GGUF
License: mit
Requirements: about 6 GB of RAM, 4.1 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
Tags: transformers gguf mistral feature-extraction en endpoints_compatible deploy:azure conversational

Numbers

3,819 downloads on Hugging Face
15 likes
license mit
4.1 GB for e5-mistral-7b-instruct-Q4_K_M.gguf

Numbers as of 2026-10-02 20:52 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
`e5-mistral-7b-instruct-Q2_K.gguf`	Q2_K	2.5 GB
`e5-mistral-7b-instruct-Q3_K_L.gguf`	Q3_K_L	3.6 GB
`e5-mistral-7b-instruct-Q3_K_M.gguf`	Q3_K_M	3.3 GB
`e5-mistral-7b-instruct-Q3_K_S.gguf`	Q3_K_S	2.9 GB
`e5-mistral-7b-instruct-Q4_0.gguf`	Q4_0	3.8 GB
`e5-mistral-7b-instruct-Q4_K_M.gguf`	Q4_K_M	4.1 GB
`e5-mistral-7b-instruct-Q4_K_S.gguf`	Q4_K_S	3.9 GB
`e5-mistral-7b-instruct-Q5_0.gguf`	Q5_0	4.7 GB
`e5-mistral-7b-instruct-Q5_K_M.gguf`	Q5_K_M	4.8 GB
`e5-mistral-7b-instruct-Q5_K_S.gguf`	Q5_K_S	4.7 GB
`e5-mistral-7b-instruct-Q6_K.gguf`	Q6_K	5.5 GB
`e5-mistral-7b-instruct-Q8_0.gguf`	Q8_0	7.2 GB
`e5-mistral-7b-instruct-f16.gguf`	F16	13 GB

From the source README

E5-Mistral-7B-Instruct-Embedding-GGUF

Original Model

intfloat/e5-mistral-7b-instruct

Run with LlamaEdge

LlamaEdge version: v0.8.2 and above

Prompt template

Prompt type: `embedding`

Context size: `4096`

Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:e5-mistral-7b-instruct-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template embedding \
    --ctx-size 4096 \
    --model-name e5-mistral-7b-instruct

Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| e5-mistral-7b-instruct-Q2_K.gguf | Q2_K | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes |
| e5-mistral-7b-instruct-Q3_K_L.gguf | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss |
| e5-mistral-7b-instruct-Q3_K_M.gguf | Q3_K_M | 3 | 3.52 GB| very small, high quality loss |
| e5-mistral-7b-instruct-Q3_K_S.gguf | Q3_K_S | 3 | 3.16 GB| very small, high quality loss |
| e5-mistral-7b-instruct-Q4_0.gguf | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [e5-mistral-7b-instruct-Q4_K_M.gguf](https://hug…

Card id model:hf:second-state/E5-Mistral-7B-Instruct-Embedding-GGUF · collected 2026-10-02 20:52 UTC · JSON