---
title: LFM2.5-1.2B-JP-202606-OptiQ-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit.md"
repository: mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit
last_updated: 2026-10-15
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - lfm2
architectures:
  - Lfm2ForCausalLM
base_model:
  - LiquidAI/LFM2.5-1.2B-JP-202606
base_model_relation: quantized
parameters: 238.0M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ja
  - en
downloads: 18
stars: 0
tags:
  - mlx
  - optiq
  - quantized
  - 4bit
  - mixed-precision
  - lfm2
  - liquid-ai
  - apple-silicon
  - on-device
  - japanese
---

# LFM2.5-1.2B-JP-202606-OptiQ-4bit

> LFM2.5-1.2B-JP-202606-OptiQ-4bit - mlx-community 在 ModelScope 开源的模型。LFM2.5-1.2B-JP-202606-OptiQ-4bit

mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit 是 ModelScope 魔搭社区上的 238.0M 参数text-generation模型，采用 other 许可，基于 LiquidAI/LFM2.5-1.2B-JP-202606 构建。

- **Repository**: mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 238.0M
- **Base model**: LiquidAI/LFM2.5-1.2B-JP-202606
- **Tags**: mlx, optiq, quantized, 4bit, mixed-precision, lfm2, liquid-ai, apple-silicon, on-device, japanese
- **Downloads**: 18
- **Stars**: 0
- **Last updated**: 2026-10-15

Source: https://www.modelscope.cn/models/mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit

---

# LFM2.5-1.2B-JP-202606-OptiQ-4bit

> Built with **[mlx-optiq](https://mlx-optiq.com)**, an MLX-native toolkit for quantizing, fine-tuning, and serving language models on Apple Silicon.
>
> Documentation: https://mlx-optiq.com/docs  
> Model collection: https://mlx-optiq.com/models

`mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit` is a mixed-precision MLX quantization of [`LiquidAI/LFM2.5-1.2B-JP-202606`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606).

The model occupies **838 MB** on disk compared to **2.34 GB** for the original bf16 release. According to the included evaluation, it achieves **58.5% pass@1 on HumanEval**.

LFM2.5 uses a hybrid architecture consisting of convolutional layers interleaved with full-attention layers. Only the attention layers maintain a KV cache. OptiQ performs mixed-precision quantization by assigning different bit widths to individual layers based on measured sensitivity.

---

# Model Summary

| Property | Value |
|---|---|
| Base model | [`LiquidAI/LFM2.5-1.2B-JP-202606`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606) |
| Architecture | Hybrid convolution + full attention (`lfm2`) |
| Framework | MLX |
| Quantization | OptiQ mixed-precision |
| Storage size | 838 MB |
| Original size | 2.34 GB (bf16) |
| Context length | 128k tokens |
| KV cache | Mixed precision (`kv_config.json`) |

---

# Evaluation

The following metrics are included with this release.

| Benchmark | Result |
|---|---:|
| MMLU (5-shot, 969 samples) | 51.0% |
| GSM8K (1000 samples) | 61.4% |
| IFEval (strict) | 71.5% |
| BFCL-V3 Simple (200 calls) | 85.5% |
| HumanEval (164 problems, pass@1) | 58.5% |
| HashHop | 0.0% |
| **Capability Score** | **54.66** |

The Capability Score is the arithmetic mean of the six benchmark scores reported above.

---

# Usage

Install the required package:

```bash
pip install mlx-optiq
```

Load the model:

```python
from mlx_lm import load, generate

model, tokenizer = load(
    "mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit"
)

prompt = tokenizer.apply_chat_template(
    [
        {
            "role": "user",
            "content": "日本の首都はどこですか？"
        }
    ],
    tokenize=False,
    add_generation_prompt=True,
)

print(
    generate(
        model,
        tokenizer,
        prompt=prompt,
        max_tokens=300,
    )
)
```

To serve the model with the bundled mixed-precision KV cache:

```bash
optiq serve \
    --model mlx-community/LFM2.5-1.2B-JP-202606-OptiQ-4bit \
    --kv-config kv_config.json
```

---

# Tool Calling

The model emits tool calls using the following format:

```text
<|tool_call_start|>[get_weather(city="Tokyo")]<|tool_call_end|>
```

When using `apply_chat_template`, tool definitions can be supplied through the `tools=` argument.

---

# Notes

- This repository contains a mixed-precision MLX quantization of the original model.
- Quantization was performed using OptiQ.
- The included `kv_config.json` contains the KV-cache precision configuration used by this release.
- Benchmark results reported above are those included with this release.

---

# Resources

- **Base model:** https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP-202606
- **mlx-optiq:** https://mlx-optiq.com
- **Documentation:** https://mlx-optiq.com/docs
- **Model collection:** https://mlx-optiq.com/models