This is the model card of NLLB-200's distilled 600M variant.
plamo-3-translate-0.8b
pfnet·Base model·released 27 Oct 2026
ollama run hf.co/pfnet/plamo-3-translate-0.8b-GGUF:Q4_K_MPLaMo 3 Translate 0.8B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.
How much VRAM does plamo-3-translate-0.8b need?
At FP16 / BF16 plamo-3-translate-0.8b needs about 2.5 GB of GPU memory.
| Quantisation | Total |
|---|---|
| 4-bitRecommended default for local use | ≈1.1 GB |
| 8-bitLossless in practice, twice the size of Q4 | ≈1.6 GB |
| FP16 / BF16recommendedFull precision, as released | ≈2.5 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.
Run plamo-3-translate-0.8b locally
--quantQ4_K_Mdefault; pick your GPU to tailor itpfnet/plamo-3-translate-0.8b-GGUF
ollama run hf.co/pfnet/plamo-3-translate-0.8b-GGUF:Q4_K_M llama-server -hf pfnet/plamo-3-translate-0.8b-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get pfnet/plamo-3-translate-0.8b-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve pfnet/plamo-3-translate-0.8b vllm serve pfnet/plamo-3-translate-0.8b-FP8services:
vllm:
image: vllm/vllm-openai:latest
command: pfnet/plamo-3-translate-0.8b
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.
from transformers import pipeline
pipe = pipeline("translation", model="pfnet/plamo-3-translate-0.8b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| pfnet/plamo-3-translate-0.8b-W4A16 | Safetensors | INT4 | — |
| pfnet/plamo-3-translate-0.8b-NVFP4 | Safetensors | NVFP4 | — |
| pfnet/plamo-3-translate-0.8b-FP8 | Safetensors | FP8 | — |
| pfnet/plamo-3-translate-0.8b-GGUF | GGUF | Q2_K | 0.4 GB |
| mradermacher/plamo-3-translate-0.8b-GGUF | GGUF | Q2_K | 0.4 GB |
| mradermacher/plamo-3-translate-0.8b-GGUF | GGUF | Q3_K_S | 0.5 GB |
| pfnet/plamo-3-translate-0.8b-GGUF | GGUF | Q3_K_M | 0.5 GB |
| mradermacher/plamo-3-translate-0.8b-GGUF | GGUF | Q3_K_M | 0.5 GB |
| mradermacher/plamo-3-translate-0.8b-GGUF | GGUF | Q3_K_L | 0.5 GB |
| mradermacher/plamo-3-translate-0.8b-GGUF | GGUF | IQ4_XS | 0.5 GB |
About plamo-3-translate-0.8b
PLaMo 3 Translate 0.8B 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 0.8B 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 0.8B 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 →Alternatives to plamo-3-translate-0.8b
All alternatives →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.
This is the model card of NLLB-200's distilled 1.3B variant.
This is the model card of IndicTrans2 En-Indic 1.1B variant.
Index-Translate-2B is the compact 2B-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.
Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations.
plamo-3-translate-0.8b FAQ
- How much VRAM does plamo-3-translate-0.8b need?
- About 2.5 GB at FP16 / BF16.
- Can plamo-3-translate-0.8b run on the RTX 4060?
- Yes. It fits at FP16 / BF16 (about 2.5 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use plamo-3-translate-0.8b 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-0.8b with Ollama or llama.cpp?
- With Ollama: ollama run hf.co/pfnet/plamo-3-translate-0.8b-GGUF:Q4_K_M. With llama.cpp: llama-server -hf pfnet/plamo-3-translate-0.8b-GGUF:Q4_K_M, which starts an OpenAI-compatible server.
Rate this model
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.
0 comments