---
title: Lens-Turbo-3.8B-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Lens-Turbo-3.8B-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Lens-Turbo-3.8B-bf16.md"
repository: mlx-community/Lens-Turbo-3.8B-bf16
last_updated: 2026-06-21
license: mit
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - microsoft/Lens-Turbo
base_model_relation: finetune
parameters: 4.1B
tensor_type:
  - BF16
library_name:
  - mlx
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 15
stars: 0
tags:
  - mlx
  - text-to-image
  - diffusion
  - lens
  - lens-turbo
  - apple-silicon
---

# Lens-Turbo-3.8B-bf16

> Lens-Turbo-3.8B-bf16 - mlx-community 在 ModelScope 开源的模型。Lens-Turbo-3.8B-bf16 (MLX)

mlx-community/Lens-Turbo-3.8B-bf16 是 ModelScope 魔搭社区上的 4.1B 参数text-to-image-synthesis模型，采用 mit 许可，基于 microsoft/Lens-Turbo 构建。

- **Repository**: mlx-community/Lens-Turbo-3.8B-bf16
- **License**: mit
- **Tasks**: text-to-image-synthesis
- **Parameters**: 4.1B
- **Base model**: microsoft/Lens-Turbo
- **Tags**: mlx, text-to-image, diffusion, lens, lens-turbo, apple-silicon
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-06-21

Source: https://www.modelscope.cn/models/mlx-community/Lens-Turbo-3.8B-bf16

---

# Lens-Turbo-3.8B-bf16 (MLX)

Apple **MLX** conversion of [microsoft/Lens-Turbo](https://huggingface.co/microsoft/Lens-Turbo) —
the **distilled 4-step** sibling of Lens (identical 3.8B DiT architecture; sample at **4 steps,
guidance 1.0**). ~8.2 GB. DiT-only (MIT); the GPT-OSS-20B encoder (Apache-2.0) and FLUX.2 VAE
load from source. Architecture is byte-identical to base Lens, which is parity-locked vs the PT
reference (DiT cosine 0.999999); this variant inherits that port.

![sample](sample.png)

## Usage

```python
from lens_mlx.pipeline_mlx import LensPipeline   # github.com/xocialize/lens-mlx

# `base` = a microsoft/Lens snapshot (tokenizer + GPT-OSS encoder + FLUX.2 VAE).
pipe = LensPipeline.from_pretrained(base, dit_repo="mlx-community/Lens-Turbo-3.8B-bf16")
img = pipe("A serene lake below snow-capped mountains, golden hour.",
           height=1024, width=1024, num_inference_steps=4, guidance_scale=1.0, seed=42)
img.save("out.png")
```

> Tip: page weights into memory before the first forward (`mx.eval` the params) when loading
> from slow/external storage, to avoid a Metal command-buffer watchdog timeout at large sizes.

## License
DiT weights MIT (from microsoft/Lens-Turbo) · GPT-OSS-20B encoder Apache-2.0 (not re-hosted) ·
FLUX.2 VAE under its own terms (not re-hosted). Upstream: [microsoft/Lens-Turbo](https://huggingface.co/microsoft/Lens-Turbo).