---
title: nomicai-modernbert-embed-base-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/nomicai-modernbert-embed-base-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/nomicai-modernbert-embed-base-6bit.md"
repository: mlx-community/nomicai-modernbert-embed-base-6bit
last_updated: 2025-04-02
license: apache-2.0
pipeline_tag: sentence-similarity
tasks:
  - sentence-similarity
model_type:
  - modernbert
architectures:
  - ModernBertModel
base_model:
  - answerdotai/ModernBERT-base
  - nomic-ai/modernbert-embed-unsupervised
base_model_relation: finetune
parameters: 32.6M
tensor_type:
  - U32
  - F16
library_name:
  - sentence-transformers
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task emb"
  - "vllm 0.9.2"
downloads: 451
stars: 0
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity
  - mteb
  - transformers.js
  - mlx
---

# nomicai-modernbert-embed-base-6bit

> nomicai-modernbert-embed-base-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/nomicai-modernbert-embed-base-6bit

mlx-community/nomicai-modernbert-embed-base-6bit 是 ModelScope 魔搭社区上的 32.6M 参数sentence-similarity模型，采用 apache-2.0 许可，基于 answerdotai/ModernBERT-base、nomic-ai/modernbert-embed-unsupervised 构建，可用 deploy_task emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/nomicai-modernbert-embed-base-6bit
- **License**: apache-2.0
- **Tasks**: sentence-similarity
- **Parameters**: 32.6M
- **Base model**: answerdotai/ModernBERT-base, nomic-ai/modernbert-embed-unsupervised
- **Inference backends**: deploy_task emb, vllm 0.9.2
- **Tags**: sentence-transformers, feature-extraction, sentence-similarity, mteb, transformers.js, mlx
- **Downloads**: 451
- **Stars**: 0
- **Last updated**: 2025-04-02

Source: https://www.modelscope.cn/models/mlx-community/nomicai-modernbert-embed-base-6bit

---

# mlx-community/nomicai-modernbert-embed-base-6bit

The Model [mlx-community/nomicai-modernbert-embed-base-6bit](https://huggingface.co/mlx-community/nomicai-modernbert-embed-base-6bit) was converted to MLX format from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) using mlx-lm version **0.0.3**.

## Use with mlx

```bash
pip install mlx-embeddings
```

```python
from mlx_embeddings import load, generate
import mlx.core as mx

model, tokenizer = load("mlx-community/nomicai-modernbert-embed-base-6bit")

# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds  # Normalized embeddings

# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)

print("Similarity matrix between texts:")
print(similarity_matrix)


```