---
title: Inkling-Small-mxfp4
canonical_url: "https://www.modelscope.cn/models/mlx-community/Inkling-Small-mxfp4"
md_url: "https://www.modelscope.cn/models/mlx-community/Inkling-Small-mxfp4.md"
repository: mlx-community/Inkling-Small-mxfp4
last_updated: 2026-07-31
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - inkling_mm_model
architectures:
  - InklingForConditionalGeneration
base_model:
  - thinkingmachines/Inkling-Small
base_model_relation: quantized
parameters: 49.5B
tensor_type:
  - U8
  - U32
  - F32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 40
stars: 0
tags:
  - mlx
---

# Inkling-Small-mxfp4

> Inkling-Small-mxfp4 - mlx-community 在 ModelScope 开源的模型。MXFP4 version of thinkingmachines/Inkling-Small.

mlx-community/Inkling-Small-mxfp4 是 ModelScope 魔搭社区上的 49.5B 参数image-text-to-text模型，基于 thinkingmachines/Inkling-Small 构建。

- **Repository**: mlx-community/Inkling-Small-mxfp4
- **Tasks**: image-text-to-text
- **Parameters**: 49.5B
- **Base model**: thinkingmachines/Inkling-Small
- **Tags**: mlx
- **Downloads**: 40
- **Stars**: 0
- **Last updated**: 2026-07-31

Source: https://www.modelscope.cn/models/mlx-community/Inkling-Small-mxfp4

---

# Inkling Small MXFP4

MXFP4 version of [thinkingmachines/Inkling-Small](https://huggingface.co/thinkingmachines/Inkling-Small).

This checkpoint uses less memory than [thinkingmachines/Inkling-Small-NVFP4](https://huggingface.co/thinkingmachines/Inkling-Small-NVFP4),
but quantizes more tensors to MXFP4. The official NVFP4 checkpoint, on the other hand, only applies 4-bit quantization to routed experts,
so quality should be better.

For the best quality, please run the official NVFP4 checkpoint directly with MLX, there's no need to convert:

```bash
mlx_vlm.generate --prompt "who are you?" --model thinkingmachines/Inkling-Small-NVFP4
```

Or, if you want to try the version in this repo (lower memory consumption, faster):

```bash
mlx_vlm.generate --prompt "who are you?" --model mlx-community/Inkling-Small-mxfp4
```

**Note**: please make sure you use the Inkling Small mlx-vlm PR.