Skip to content
Computer vision

Labadain-Gemma-4-E3B-it-Tetun

разговорная Gemma 4 для языка тетум

1 min readupdated

Labadain-Gemma-4 — это Gemma 4 на 5,12 млрд параметров, дообученная для диалогов на тетумском языке (Tetun). Модель создана для общих знаний, новостей, повседневных разговоров и тем здоровья, а также для исследований и образовательных проектов для Восточного Тимора.

Ключевые особенности

  • Дообучена под тетумский язык на многоходовых диалогах и QA-данных.
  • Основа — unsloth/gemma-4-E2B-it; использован QLoRA, адаптеры объединены с базовой моделью.
  • Финальный датасет — 32 197 многоходовых диалогов: новости, здоровье, образование и язык, общие беседы.
  • Есть GGUF-версия Q4_K_M для локального и CPU-инференса, а также вариант для Ollama.
  • Режим рассуждений можно отключать через enable_thinking=False или --think=false.

Пример

ollama run labadainofficial/labadain-gemma4:e3b-q4km --think=false
ПодробнееБенчмарков в карточке нет; модель ещё не оценивали на downstream-приложениях.
Обучение: QLoRA на 32 197 диалогах; финальные веса объед��нены с базовой моделью.
Для локального запуска доступны GGUF Q4_K_M и Ollama; в примере Unsloth — max_seq_length=4096 и загрузка в 4-bit.
Это производная Gemma 4, поэтому нужно соблюдать условия upstream-лицензии.
Discuss Telegram 0 473

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 9.5 GB · ready files11 GB
  • FP8 / INT8recommendedweights 4.8 GB5.7 GB
  • 4-bitweights 2.7 GB3.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2080 Ti

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # labadain/Labadain-Gemma-4-E3B-it-Tetun
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download labadain/Labadain-Gemma-4-E3B-it-Tetun --local-dir ~/models/Labadain-Gemma-4-E3B-it-Tetun
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

  1. gemma-4-E2Bfamily root
  2. gemma-4-E2B-it
  3. gemma-4-E2B-it
  4. Labadain-Gemma-4-E3B-it-Tetun

New posts about versions of gemma-4-E2B (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face

About the model

labadain/Labadain-Gemma-4-E3B-it-Tetun
Author
labadain
Category
Computer vision
Released
Posted

On NeyroLearn

Hugging Face

4730

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments