---
title: Mellum2-12B-A2.5B-Instruct-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Instruct-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Instruct-bf16.md"
repository: mlx-community/Mellum2-12B-A2.5B-Instruct-bf16
last_updated: 2026-08-12
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mellum
architectures:
  - MellumForCausalLM
base_model:
  - JetBrains/Mellum2-12B-A2.5B-Instruct
base_model_relation: quantized
parameters: 12.1B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 22
stars: 0
tags:
  - mlx
  - mellum
  - moe
  - instruct
  - bf16
---

# Mellum2-12B-A2.5B-Instruct-bf16

> Mellum2-12B-A2.5B-Instruct-bf16 - mlx-community 在 ModelScope 开源的模型。Mellum2 12B A2.5B Instruct - BF16 MLX

mlx-community/Mellum2-12B-A2.5B-Instruct-bf16 是 ModelScope 魔搭社区上的 12.1B 参数text-generation模型，采用 apache-2.0 许可，基于 JetBrains/Mellum2-12B-A2.5B-Instruct 构建。

- **Repository**: mlx-community/Mellum2-12B-A2.5B-Instruct-bf16
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 12.1B
- **Base model**: JetBrains/Mellum2-12B-A2.5B-Instruct
- **Tags**: mlx, mellum, moe, instruct, bf16
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2026-08-12

Source: https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Instruct-bf16

---

# Mellum2 12B A2.5B Instruct - BF16 MLX

This is an MLX conversion of
[JetBrains/Mellum2-12B-A2.5B-Instruct](https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Instruct),
stored in bfloat16 without weight quantization.

Mellum2 Instruct is a Mixture-of-Experts assistant model with 64 experts and
8 active experts per token. It supports a 131,072-token context window and is
optimized for direct instruction following.

## Conversion details

- Source: `JetBrains/Mellum2-12B-A2.5B-Instruct`
- Format: MLX safetensors
- Precision: bfloat16
- Quantization: none
- License: Apache-2.0
- EOS token: `<|im_end|>` (token ID 28)

The upstream `config.json` and `generation_config.json` identify token ID 0 as
the EOS token, while the tokenizer identifies `<|im_end|>` (ID 28) as EOS.
This conversion uses token ID 28 so MLX generation stops at the end of the
assistant turn.

## Usage

```bash
pip install -U mlx-lm

mlx_lm.chat \
  --model mlx-community/Mellum2-12B-A2.5B-Instruct-bf16 \
  --max-tokens 8192 \
  --temp 0.6 \
  --top-p 0.95
```

## Model provenance

For the original model card, training details, benchmark results, and usage
guidance, see the
[upstream JetBrains checkpoint](https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Instruct).