metadata
license: apache-2.0
base_model: Qwen/Qwen3-Embedding-8B
tags:
- transformers
- sentence-transformers
- sentence-similarity
- feature-extraction
- text-embeddings-inference
- mlx
library_name: mlx
pipeline_tag: text-generation
jedisct1/Qwen3-Embedding-8B-q8-mlx
This model jedisct1/Qwen3-Embedding-8B-q8-mlx was converted to MLX format from Qwen/Qwen3-Embedding-8B using mlx-lm version 0.30.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("jedisct1/Qwen3-Embedding-8B-q8-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)