selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

pfnet logo

plamo-3-translate-31b

pfnet·Base model·released 26 Oct 2026

plamo-community-license31.8B256K ctx ≈38 GB
Your GPU
ollama run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M
All 5 runners ↓

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

How much VRAM does plamo-3-translate-31b need?

At Q8_0 plamo-3-translate-31b needs about 38 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use18 GB file≈22 GB
8-bitrecommendedLossless in practice, twice the size of Q431 GB est.≈38 GB
FP16 / BF16Full precision, as released59 GB est.≈71 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

Can the Tesla P40 run plamo-3-translate-31b? →

Run plamo-3-translate-31b locally

--quantQ4_K_Mdefault; pick your GPU to tailor itpfnet/plamo-3-translate-31b-GGUF

Q4_K_M straight from Hugging Facedocs
ollama run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M

Install Ollama

OpenAI-compatible server with a web UIdocs
llama-server -hf pfnet/plamo-3-translate-31b-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Download with the lms CLIdocs
lms get pfnet/plamo-3-translate-31b-GGUF@Q4_K_M

Then load it from the LM Studio app or with `lms load`.

Install LM Studio

Serve an OpenAI-compatible APIdocs
vllm serve pfnet/plamo-3-translate-31b
Smaller FP8 builddocs
vllm serve pfnet/plamo-3-translate-31b-FP8
Docker Compose (NVIDIA)docs
yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: pfnet/plamo-3-translate-31b
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

Install vLLM

Run with the translation pipelinedocs
python
from transformers import pipeline

pipe = pipeline("translation", model="pfnet/plamo-3-translate-31b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Install Transformers

Quantised versions and downloads

About plamo-3-translate-31b

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.

Full model card on Hugging Face →

Other Plamo 3 Translate models

Whole family →
pfnet logo890MConditions≈2.5 GB↓ 3.8K
pfnet logo8.5BConditions≈11 GB↓ 1.6K

Alternatives to plamo-3-translate-31b

All alternatives →
tencent logo

Hy-MT2-30B-A3B

tencent·Translation

≈36 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.

30.1BA3B256K ctx Apache 2.0
5.5KMay 2026gguf
tencent logo

Hy-SimulMT-30B-A3B

tencent·Translation

≈37 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.

30.4BA3B256K ctx Apache 2.0
1.3KOct 2026
IndexTeam logo

Index-Translate-9B

IndexTeam·Translation

≈12 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.

9.7B256K ctx Apache 2.0
2.2KSept 2026gguf
tencent logo

Hy-MT2-7B

tencent·Translation

≈10 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.

8B256K ctx Apache 2.0
31.4KMay 2026gguf
facebook logo

nllb-moe-54b

facebook·Translation

≈65 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…

54B1K ctx CC BY-NC 4.0
2.4KMar 2023
ModelSpace logo

GemmaX2-28-9B-v0.1

ModelSpace·Translation

≈13 GB

New multilingual machine translation model (MiLMMT-46) is now available. Please check the link for detailed information.

10.2B8K ctx Gemma Terms of Use
4KNov 2024gguf

plamo-3-translate-31b 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.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.