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.

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. nvidia logo

    canary-1b

    nvidia·STT

    ≈2.7 GB

    NVIDIA NeMo Canary is a family of multi-lingual multi-tasking models that achieves state-of-the art performance on multiple benchmarks.

    1BCC BY-NC 4.0
    2.8KFeb 2024gguf
    • Related category
    • Similar size (1B vs 890M)
    vs
  2. Systran logo≈4.0 GB

    This repository contains the conversion of openai/whisper-large-v2 to the CTranslate2 model format.

    1.6BMIT
    135.8KNov 2023
    • Related category
    • Similar size (1.6B vs 890M)
    • Commercial use OK
    vs
  3. mistralai logo≈5.8 GB

    Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech-transcription model and among the first open-source solutions to achieve accuracy comparable to offline systems with a delay of <500ms.

    4.4BApache 2.0
    1.5MJan 2026gguf
    • Related category
    • Larger (4.4B vs 890M)
    • Commercial use OK
    • Widely used
    vs
  4. nvidia logo

    canary-qwen-2.5b

    nvidia·STT

    ≈6.2 GB

    NVIDIA NeMo Canary-Qwen-2.5B is an English speech recognition model that achieves state-of-the art performance on multiple English speech benchmarks.

    2.6BCC BY 4.0
    25KJun 2025gguf
    • Related category
    • Larger (2.6B vs 890M)
    • Commercial use OK
    vs
  5. facebook logo≈5.7 GB

    SeamlessM4T is our foundational all-in-one Massively Multilingual and Multimodal Machine Translation model delivering high-quality translation for speech and text in nearly 100 languages.

    2.3BCC BY-NC 4.0
    342.9KNov 2023
    • Related category
    • Larger (2.3B vs 890M)
    vs
  6. Systran logo≈1.1 GB

    This repository contains the conversion of openai/whisper-small to the CTranslate2 model format.

    244MMIT
    6.6MNov 2023
    • Related category
    • Smaller (244M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  7. openai logo

    whisper-small

    openai·STT

    ≈1.0 GB

    Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.

    242MApache 2.0
    4.3MSept 2022gguf
    • Related category
    • Smaller (242M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  8. Systran logo≈1.1 GB

    This repository contains the conversion of openai/whisper-small.en to the CTranslate2 model format.

    244MMIT
    1.7MNov 2023
    • Related category
    • Smaller (244M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  9. Systran logo≈1.4 GB

    This repository contains the conversion of distil-whisper/distil-medium.en to the CTranslate2 model format.

    394MMIT
    7.4KJan 2024
    • Related category
    • Smaller (394M vs 890M)
    • Commercial use OK
    vs
  10. mistralai logo≈5.8 GB

    Voxtral Mini 4B Realtime Arabic is a streaming speech-to-text model for Arabic dialects and Modern Standard Arabic. It is designed to handle challenging real-world audio and code-switching, where speakers alternate between languages within the same conversation.

    4.4BUnknown licence
    2.2KOct 2026gguf
    • Related category
    • Larger (4.4B vs 890M)
    vs
  11. nvidia logo≈0.9 GB

    NVIDIA NeMo Canary Flash [1] is a family of multilingual multi-tasking models based on Canary architecture [2] that achieves state-of-the art performance on multiple speech benchmarks.

    180MCC BY 4.0
    2.8KMar 2025gguf
    • Related category
    • Smaller (180M vs 890M)
    • Commercial use OK
    vs
  12. openai logo

    whisper-base

    openai·STT

    ≈0.7 GB

    Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.

    73MApache 2.0
    6.2MSept 2022gguf
    • Related category
    • Smaller (73M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  13. Systran logo≈0.7 GB

    This repository contains the conversion of openai/whisper-base to the CTranslate2 model format.

    74MMIT
    2.7MNov 2023
    • Related category
    • Smaller (74M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  14. Systran logo≈0.6 GB

    This repository contains the conversion of openai/whisper-tiny to the CTranslate2 model format.

    39MMIT
    2.3MNov 2023
    • Related category
    • Smaller (39M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  15. Systran logo≈0.7 GB

    This repository contains the conversion of openai/whisper-base.en to the CTranslate2 model format.

    74MMIT
    1.5MNov 2023
    • Related category
    • Smaller (74M vs 890M)
    • Commercial use OK
    • Widely used
    vs
  16. Unbabel logo

    Tower-Plus-9B

    Unbabel·Chat

    ≈8.6 GB

    Tower+ 9B is build on top of Gemma 2 9B. The model goes through the Continuous Pretraining (CPT), Instruction Tuning (IT), Weighted Preference Optimization (WPO). During all stages we include parallel and multilingual data (covering 22 languages).

    9.2B8K ctx CC BY-NC-SA 4.0
    16.9KJun 2025gguf
    • Related category
    • Larger (9.2B vs 890M)
    vs
  17. Data Freshness: The pre-training data has a cutoff date of June 25, 2025.

    63.2BA3BNVIDIA Open Model License
    726Apr 2026
    • Related category
    • Larger (63.2B vs 890M)
    • Commercial use OK
    vs
  18. Systran logo≈0.6 GB

    This repository contains the conversion of openai/whisper-tiny.en to the CTranslate2 model format.

    39MMIT
    461.4KNov 2023
    • Related category
    • Smaller (39M vs 890M)
    • Commercial use OK
    vs
  19. CohereLabs logo≈70 GB

    Cohere Labs Command A Translate is an open weights research release of a 111 billion parameter model that achieves state-of-the-art performance on translation quality.

    111BCC BY-NC 4.0
    14Aug 2025gguf
    • Related category
    • Larger (111B vs 890M)
    vs
  20. facebook logo

    seamless-m4t-large

    facebook·STT

    ? GB

    SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

    ?BCC BY-NC 4.0
    0Aug 2023
    • Related category
    vs
  21. facebook logo

    seamless-m4t-medium

    facebook·STT

    ? GB

    SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

    ?BCC BY-NC 4.0
    0Aug 2023
    • Related category
    vs
  22. ggerganov logo

    whisper.cpp

    ggerganov·STT

    ? GB

    whisper.cpp is an open-weight stt model from ggerganov, published on Hugging Face.

    ?BMIT
    0Mar 2023
    • Related category
    • Commercial use OK
    vs