---
title: plamo-2-translate-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/plamo-2-translate-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/plamo-2-translate-8bit.md"
repository: mlx-community/plamo-2-translate-8bit
last_updated: 2026-10-12
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - plamo2
architectures:
  - Plamo2ForCausalLM
base_model:
  - pfnet/plamo-2-translate
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ja
downloads: 359
stars: 0
tags:
  - mlx
  - plamo
  - translation
  - custom_code
  - 8-bit
---

# plamo-2-translate-8bit

> plamo-2-translate-8bit - mlx-community 在 ModelScope 开源的模型。PLaMo 2 Translate — MLX 8bit

mlx-community/plamo-2-translate-8bit 是 ModelScope 魔搭社区上的text-generation模型，采用 other 许可，基于 pfnet/plamo-2-translate 构建。

- **Repository**: mlx-community/plamo-2-translate-8bit
- **License**: other
- **Tasks**: text-generation
- **Base model**: pfnet/plamo-2-translate
- **Tags**: mlx, plamo, translation, custom_code, 8-bit
- **Downloads**: 359
- **Stars**: 0
- **Last updated**: 2026-10-12

Source: https://www.modelscope.cn/models/mlx-community/plamo-2-translate-8bit

---

# PLaMo 2 Translate — MLX 8bit

A standalone MLX conversion of [pfnet/plamo-2-translate](https://huggingface.co/pfnet/plamo-2-translate) for Apple Silicon. Affine 8-bit quantization, group size 64, with BF16 floating parameters and activations. The recurrent SSM state and the exponentiation of `A_log` use FP32. This model specializes in translation.

## October 7, 2026 update

Regenerated from source revision `cae8da342a3e051ed69f90ce24c23eacff908732`, using MLX 0.31.1 and mlx-lm 0.31.2. The prior repository revision remains available at [`84f3a775383c115fa91d82c36fc813de85b755d7`](https://huggingface.co/mlx-community/plamo-2-translate-8bit/tree/84f3a775383c115fa91d82c36fc813de85b755d7).

The bundled [`modeling_mlx_plamo2.py`](modeling_mlx_plamo2.py) is selected by `config.json`'s `model_file`. It applies the checkpoint's RoPE bases (1,000,000 here) and PLaMo's unbounded `softplus(dt + bias)` SSM time steps. The prompt includes BOS, and EOS IDs include both 1 and the operation delimiter 4. It uses the upstream convolution; no experimental fusion or all-FP16 conversion is enabled.

The template supports ordinary user/assistant messages and explicit PLaMo `input lang=...` / `output lang=...` messages. Both forms produce the same tested prompt when language labels are specified. The vocabulary and source training are unchanged.

## Usage

Tested with Python 3.13 on Apple Silicon:

```sh
pip install 'mlx==0.31.1' 'mlx-lm==0.31.2' 'transformers>=4.46,<5' numba
```

```python
from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load(
    "mlx-community/plamo-2-translate-8bit",
    tokenizer_config={"trust_remote_code": True},
)
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Write the text to be translated here."}],
    tokenize=True,
    add_generation_prompt=True,
    source_language="English",
    target_language="Japanese",
)
print(generate(
    model, tokenizer, prompt=prompt, sampler=make_sampler(temp=0),
    max_tokens=2048, prefill_step_size=512,
))
```

Omitting language labels retains English/Japanese automatic direction. Explicit labels are recommended for reproducible comparisons. Inference corrections require a runtime that honors `config.model_file`, as mlx-lm 0.31.2 does. Runtimes that instantiate their own generic PLaMo 2 implementation may differ. This repository targets MLX; the included original Transformers source does not establish PyTorch compatibility for these MLX parameter layouts.

## Validation

The full supplied English-to-Japanese corporate-profile example was validated on an Apple M1 Max with 32 GPU cores and 64 GB memory. Greedy decoding, prompt length 364, prefill chunk 512, generation limit 2048, two warmed standalone runs.

| Check | Result |
| --- | --- |
| Full output versus corrected direct inference at the same precision | Exact byte match in both runs |
| Structured versus natural-message prompt | Exact token match |
| Completion | EOS; all 8 paragraphs present |
| Required names and phrase | Preferred Networks, both founders, Learn or Die retained |
| chrF against the supplied Japanese reference | 73.94 |
| Weight files | 10.12 GB |
| Tensor dtypes | BF16, U32 |

See [`evaluation.json`](evaluation.json) for the exact runs, versions and source revision. The machine was shared with another workload; elapsed times and throughput are observational, not a controlled speed comparison. Complete streaming and non-streaming CLI outputs were also checked against the same direct-inference output before publication.

This is one example, not a broad quality benchmark. The output differs from the supplied Japanese reference and is not guaranteed to match BF16. Output equality is with the corresponding same-precision corrected implementation; it does not imply equality across quantization levels. The previous public 8bit weights were not included in this comparison, so these checks do not establish superiority over that release.

## Source, license, and limitations

PLaMo Translation Model was developed by Preferred Networks. See the [technical announcement](https://tech.preferred.jp/ja/blog/plamo-translate/) and [press release](https://www.preferred.jp/ja/news/pr20250527/).

The original [PLaMo community license](https://plamo.preferredai.jp/info/plamo-community-license-en) applies. License files are included in [`LICENSE`](LICENSE); a [Japanese version](https://plamo.preferredai.jp/info/plamo-community-license-ja) is also available. Consult the source model's license and [commercial-use contact form](https://forms.gle/mTL8tBLrMYXKNZD56) as applicable.

This model is not instruction-tuned for general dialogue. It may produce inaccurate, biased, or otherwise unsuitable translations; the source model's documented limitations continue to apply.

The source model was trained under “Research and Development Project of the Enhanced Infrastructures for Post 5G Information and Communication System” (JPNP 20017), subsidized by NEDO.