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.

Alternatives to plamo-3-translate-0.8b

70 open-weight models that do the same job as plamo-3-translate-0.8b (890M translation), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.

Compare plamo-3-translate-0.8b with the top 3
the original
pfnet logo

plamo-3-translate-0.8b

pfnet·Translation

≈2.5 GB

PLaMo 3 Translate 0.8B is a translation-specialized LLM developed by Preferred Networks (PFN) that delivers world-class translation quality.

890M256K ctx plamo-community-license
3.8KOct 2026gguf
--vram
any
--gpus
--quant
  1. facebook logo

    nllb-200-distilled-600M

    facebook·Translation

    ≈1.8 GB

    This is the model card of NLLB-200's distilled 600M variant.

    600M1K ctx CC BY-NC 4.0
    732.9KJul 2022gguf
    • Same category
    • Similar size (600M vs 890M)
    vs
  2. tencent logo

    Hy-MT2-1.8B

    tencent·Translation

    ≈5.1 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.

    2B256K ctx Apache 2.0
    21.4KMay 2026gguf
    • Same category
    • Larger (2B vs 890M)
    • Commercial use OK
    vs
  3. facebook logo

    nllb-200-distilled-1.3B

    facebook·Translation

    ≈3.4 GB

    This is the model card of NLLB-200's distilled 1.3B variant.

    1.3B1K ctx CC BY-NC 4.0
    298.7KJul 2022gguf
    • Same category
    • Similar size (1.3B vs 890M)
    vs
  4. ai4bharat logo

    indictrans2-en-indic-1B

    ai4bharat·Translation

    ≈3.0 GB

    This is the model card of IndicTrans2 En-Indic 1.1B variant.

    1.1BMIT
    49KSept 2023
    • Same category
    • Similar size (1.1B vs 890M)
    • Commercial use OK
    vs
  5. IndexTeam logo

    Index-Translate-2B

    IndexTeam·Translation

    ≈5.6 GB

    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.

    2.3B256K ctx Apache 2.0
    2.1KSept 2026gguf
    • Same category
    • Larger (2.3B vs 890M)
    • Commercial use OK
    vs
  6. tencent logo

    HY-MT1.5-1.8B

    tencent·Translation

    ≈5.1 GB

    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.

    2B256K ctx Unknown licence
    4.8KDec 2025gguf
    • Same category
    • Larger (2B vs 890M)
    vs
  7. LiquidAI logo

    LFM2-350M-ENJP-MT

    LiquidAI·Translation

    ≈1.3 GB

    Based on the LFM2-350M model, this checkpoint has been fine-tuned for near real-time bi-directional Japanese/English translation of short-to-medium inputs.

    354M125K ctx lfm1.0
    1KSept 2025gguf
    • Same category
    • Smaller (354M vs 890M)
    vs
  8. kyutai logo

    hibiki-2b-pytorch-bf16

    kyutai·Translation

    ≈5.0 GB

    Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time…

    2BCC BY 4.0
    1.5KFeb 2025
    • Same category
    • Larger (2B vs 890M)
    • Commercial use OK
    vs
  9. google-t5 logo

    t5-base

    google-t5·Translation

    ≈1.0 GB

    With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input.

    223M512 ctx Apache 2.0
    2.8MMar 2022gguf
    • Same category
    • Smaller (223M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  10. ai4bharat logo

    indictrans2-en-indic-dist-200M

    ai4bharat·Translation

    ≈1.1 GB

    This is the model card of IndicTrans2 En-Indic Distilled 200M variant.

    275MMIT
    310.2KSept 2023
    • Same category
    • Smaller (275M vs 890M)
    • Commercial use OK
    vs
  11. sarvamai logo

    sarvam-translate

    sarvamai·Translation

    ≈5.6 GB

    Sarvam-Translate is an advanced translation model built by Sarvam AI in partnership with AI4Bharat, specifically designed for comprehensive, document-level translation across the 22 official Indian languages, built on Gemma3-4B-IT.

    4.3B128K ctx GPL 3.0
    65.2KJun 2025gguf
    • Same category
    • Larger (4.3B vs 890M)
    • Commercial use OK
    vs
  12. Helsinki-NLP logo

    opus-mt-en-ru

    Helsinki-NLP·Translation

    ? GB

    opus-mt-en-ru is an open-weight translation model from Helsinki-NLP, published on Hugging Face.

    ?B512 ctx Apache 2.0
    589.5KMar 2022
    • Same category
    • Commercial use OK
    vs
  13. Helsinki-NLP logo

    opus-mt-zh-en

    Helsinki-NLP·Translation

    ? GB

    This model can be used for translation and text-to-text generation.

    ?B512 ctx CC BY 4.0
    387.4KMar 2022
    • Same category
    • Commercial use OK
    vs
  14. Helsinki-NLP logo

    opus-mt-de-en

    Helsinki-NLP·Translation

    ? GB

    opus-mt-de-en is an open-weight translation model from Helsinki-NLP, published on Hugging Face.

    ?B512 ctx Apache 2.0
    353.9KMar 2022gguf
    • Same category
    • Commercial use OK
    vs
  15. Helsinki-NLP logo

    opus-mt-en-de

    Helsinki-NLP·Translation

    ? GB

    Model Description: - Developed by: Language Technology Research Group at the University of Helsinki - Model Type: Translation - Language(s): - Source Language: English - Target Language: German - License: CC-BY-4.0 - Resources for more information: - GitHub Repo

    ?B512 ctx CC BY 4.0
    287.9KMar 2022gguf
    • Same category
    • Commercial use OK
    vs
  16. 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
    • Same category
    • Larger (8B vs 890M)
    • Commercial use OK
    vs
  17. google-t5 logo

    t5-small

    google-t5·Translation

    ≈0.6 GB

    With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input.

    61M512 ctx Apache 2.0
    17.7MMar 2022gguf
    • Same category
    • Smaller (61M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  18. ModelSpace logo

    GemmaX2-28-2B-v0.1

    ModelSpace·Translation

    ≈4.3 GB

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

    3.2B8K ctx Gemma Terms of Use
    103Nov 2024gguf
    • Same category
    • Larger (3.2B vs 890M)
    vs
  19. 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
    • Same category
    • Larger (9.7B vs 890M)
    • Commercial use OK
    vs
  20. 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
    • Same category
    • Larger (30.1B vs 890M)
    • Commercial use OK
    vs
  21. Unbabel logo

    wmt22-comet-da

    Unbabel·Translation

    ? GB

    This is a COMET evaluation model: It receives a triplet with (source sentence, translation, reference translation) and returns a score that reflects the quality of the translation compared to both source and reference.

    ?BApache 2.0
    8.7KFeb 2023
    • Same category
    • Commercial use OK
    vs
  22. 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
    • Same category
    • Larger (30.4B vs 890M)
    • Commercial use OK
    vs
  23. Unbabel logo

    wmt22-cometkiwi-da

    Unbabel·Translation

    ? GB

    This is a COMET quality estimation model: It receives a source sentence and the respective translation and returns a score that reflects the quality of the translation.

    ?BCC BY-NC-SA 4.0
    4KFeb 2023
    • Same category
    vs
  24. tencent logo

    Hunyuan-MT-7B

    tencent·Translation

    ≈10 GB

    Hunyuan-MT-Chimera-7B-fp8 was produced by AngelSlim. The Hunyuan Translation Model comprises a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera.

    8B32K ctx Unknown licence
    3.5KAug 2025gguf
    • Same category
    • Larger (8B vs 890M)
    vs