---
title: Mellum2-12B-A2.5B-Thinking-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Thinking-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Thinking-6bit.md"
repository: mlx-community/Mellum2-12B-A2.5B-Thinking-6bit
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-Thinking
base_model_relation: quantized
parameters: 2.7B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 17
stars: 0
tags:
  - mlx
  - mellum
  - moe
  - thinking
  - 6-bit
---

# Mellum2-12B-A2.5B-Thinking-6bit

> Mellum2-12B-A2.5B-Thinking-6bit - mlx-community 在 ModelScope 开源的模型。Mellum2 12B A2.5B Thinking - 6-bit MLX

mlx-community/Mellum2-12B-A2.5B-Thinking-6bit 是 ModelScope 魔搭社区上的 2.7B 参数text-generation模型，采用 apache-2.0 许可，基于 JetBrains/Mellum2-12B-A2.5B-Thinking 构建。

- **Repository**: mlx-community/Mellum2-12B-A2.5B-Thinking-6bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 2.7B
- **Base model**: JetBrains/Mellum2-12B-A2.5B-Thinking
- **Tags**: mlx, mellum, moe, thinking, 6-bit
- **Downloads**: 17
- **Stars**: 0
- **Last updated**: 2026-08-12

Source: https://www.modelscope.cn/models/mlx-community/Mellum2-12B-A2.5B-Thinking-6bit

---

# Mellum2 12B A2.5B Thinking - 6-bit MLX

This is a 6-bit affine MLX quantization of
[JetBrains/Mellum2-12B-A2.5B-Thinking](https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking).

Mellum2 Thinking is a reasoning-augmented Mixture-of-Experts assistant model.
It has 64 experts with 8 active per token, a 131,072-token context window, and
emits reasoning in `<think>...</think>` blocks before the final answer.

## Conversion details

- Source: `JetBrains/Mellum2-12B-A2.5B-Thinking`
- Format: MLX safetensors
- Quantization: affine, 6 bits, group size 64
- 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-Thinking-6bit \
  --max-tokens 8192 \
  --temp 0.6 \
  --top-p 0.95
```

## Benchmarks

Benchmarked with oMLX 0.5.7 and MLX-LM 0.31.3 on an Apple M5 Max MacBook
Pro with 128 GB unified memory, using the built-in Python-code workload and
128 generated tokens. Results vary with hardware, runtime versions, context
length, and generation settings.

| Prompt tokens | TTFT | Prefill | Generation | End-to-end | Peak memory |
| ---: | ---: | ---: | ---: | ---: | ---: |
| 4,096 | 717.8 ms | 5,706.1 tok/s | 145.9 tok/s | 1.6 s | 9.90 GB |
| 16,384 | 3,436.8 ms | 4,767.2 tok/s | 132.8 tok/s | 4.4 s | 10.2 GB |
| 32,768 | 9,389.4 ms | 3,489.9 tok/s | 114.7 tok/s | 10.5 s | 10.5 GB |
| 65,536 | 23,584.3 ms | 2,778.8 tok/s | 87.4 tok/s | 25.1 s | 11.2 GB |
| 131,072 | 69,353.6 ms | 1,889.9 tok/s | 54.9 tok/s | 71.7 s | 12.7 GB |

At a 4,096-token prompt, batch generation achieved 196.4, 187.8, and 194.2
aggregate generation tok/s at 2, 4, and 8 concurrent requests, respectively,
compared with 145.9 tok/s for one request.

## 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-Thinking).