# plamo-3-translate-31b

> PLaMo 3 Translate 31B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.

- **Organisation:** pfnet
- **Category:** Translation
- **Parameters:** 31.8B
- **Context length:** 262,144 tokens
- **Licence:** plamo-community-license (Commercial use with conditions)
- **Released:** 2026-10-26
- **Hugging Face:** 1K downloads (30 days), 31 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q4_K_M | 22.02 |
| Q8_0 | 38.21 |
| F16 | 71.48 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [MLX](https://github.com/ml-explore/mlx-lm)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

PLaMo 3 Translate 31B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality. It is built on PLaMo 3 NICT, a pretrained model developed through joint research by PFN and the National Institute of Information and Communications Technology (NICT). We further trained this base model on tens of billions of tokens of translation-focused data. For development details, see the tech blog.

PLaMo 3 Translate 31B supports translation among 53 languages (see Supported Languages). It can also take surrounding context and a glossary into account, and lets you choose between plain and polite style for Japanese output. The maximum length during training was 32,768 tokens for the input and output combined. The model can translate long passages in one go, but split anything longer so that the input and output together stay within this limit.

PLaMo 3 Translate 31B is available under the PLaMo Community License. Personal use, such as learning or hobby projects, and other non-commercial use, including academic use, are free of charge with no prior registration. See License for the terms of commercial use.

## Alternatives

- [tencent/Hy-MT2-30B-A3B](https://selfhost.directory/models/tencent/hy-mt2-30b-a3b) (30.1B (3B active), Apache 2.0, ≈36.2 GB): Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages.
- [tencent/Hy-SimulMT-30B-A3B](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b) (30.4B (3B active), Apache 2.0, ≈36.59 GB): Hy-SimulMT is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting bidirectional speech-to-speech translation between Chinese and English. It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech.
- [IndexTeam/Index-Translate-9B](https://selfhost.directory/models/indexteam/index-translate-9b) (9.7B, Apache 2.0, ≈11.96 GB): Index-Translate-9B is the 9B-parameter multilingual text model of the Index-Translate family, built on Qwen3.5. It supports text translation across 150 languages and follows translation instructions involving terminology, formatting, style, structure, context, and output length.
- [tencent/Hy-MT2-7B](https://selfhost.directory/models/tencent/hy-mt2-7b) (8B, Apache 2.0, ≈10.03 GB): Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages.
- [facebook/nllb-moe-54b](https://selfhost.directory/models/facebook/nllb-moe-54b) (54B, CC BY-NC 4.0, ≈64.62 GB): The NLLB model was presented in No Language Left Behind: Scaling Human-Centered Machine Translation by Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek…
- [ModelSpace/GemmaX2-28-9B-v0.1](https://selfhost.directory/models/modelspace/gemmax2-28-9b-v0.1) (10.2B, Gemma Terms of Use, ≈12.56 GB): New multilingual machine translation model (MiLMMT-46) is now available. Please check the link for detailed information.

More: https://selfhost.directory/models/pfnet/plamo-3-translate-31b/alternatives

## Runs well on

- [Tesla P40](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/tesla-p40): Q4_K_M
- [Radeon RX 7900 XTX](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rx-7900-xtx): Q4_K_M
- [Instinct MI50 32GB](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/instinct-mi50): Q4_K_M
- [GeForce RTX 5090](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rtx-5090): Q4_K_M
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/apple-m4-pro-48gb): Q4_K_M
- [RTX A6000](https://selfhost.directory/models/pfnet/plamo-3-translate-31b/on/rtx-a6000): Q8_0

## Similar size

- [tencent/Hy-MT2-30B-A3B](https://selfhost.directory/models/tencent/hy-mt2-30b-a3b) (30.1B)
- [tencent/Hy-SimulMT-30B-A3B](https://selfhost.directory/models/tencent/hy-simulmt-30b-a3b) (30.4B)

## FAQ

**How much VRAM does plamo-3-translate-31b need?**
About 38 GB at Q8_0. Full precision needs about 71 GB.

**Can plamo-3-translate-31b run on the Tesla P40?**
Yes. It fits at Q4_K_M (about 22 GB). It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.

**Can I use plamo-3-translate-31b commercially?**
Yes, with conditions. It is released under plamo-community-license. Custom licence: read the model card before using it commercially.

**How do I run plamo-3-translate-31b with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M. With llama.cpp: llama-server -hf pfnet/plamo-3-translate-31b-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/pfnet/plamo-3-translate-31b
- homepage: https://www.preferred.jp/en/blog/tech/plamo-3-translate-weight-release

---
Source: https://selfhost.directory/models/pfnet/plamo-3-translate-31b