TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Models
Family
Gemma

Gemma models

Browse all models from this model family.

All models
to
  • Gen 7Gemma
    TranslateGemma
    By Google
    TranslateGemma is Google’s Gemma 3 based open translation suite, with 4B, 12B and 27B models that translate across 55 languages and can also translate text inside images, from phones up to cloud servers.
    NewText
    Released 1mo ago
  • Gen 7Gemma
    MedGemma 1.5
    By Google
    MedGemma 1.5 4B is Google’s updated 4B-parameter medical vision-language model that improves CT, MRI and histopathology understanding while remaining compute efficient for offline and cloud healthcare text and imaging workflows.
    NewText
    Released 1mo ago
  • Gen 7Gemma
    Gemma Scope 2
    By Google
    Gemma Scope 2 is Google DeepMind’s open interpretability suite of sparse autoencoders and transcoders for Gemma 3, letting researchers inspect features and circuits across all layers to study safety-relevant behavior.
    NewText
    Released 1mo ago
  • Gen 7Gemma
    T5Gemma 2
    By Google
    T5Gemma 2 is Google’s next generation Gemma 3 based encoder-decoder family, a lightweight multilingual and multimodal LLM that reads text and images, outputs text, and offers 128K context with tied embeddings and merged attention for efficient on-device deployment.
    NewText
    Released 2mo ago
  • Gen 3Gemma
    Gemma 3n
    By Google
    Gemma 3n is the “nano” edition of Google’s Gemma 3 family—an open-weight, on-device–friendly model tuned for fast reasoning and coding at low memory cost. It supports long-context prompts, function/tool calling, and structured (JSON) outputs, making it great for mobile/edge copilots and lightweight agents.
    Text
    Released 9mo ago
  • Gen 3Gemma
    PaliGemma 2
    By Google
    PaliGemma 2 is Google’s next-gen open-weight vision-language model in the Gemma family. It takes images (docs, charts, screenshots, photos) plus text and answers in text—with stronger OCR, grounded visual reasoning, multi-image understanding, and easy fine-tuning for real apps on a single GPU or edge devices.
    Text
    Released 1y ago
  • Gen 7Gemma
    Gemma 2
    By Google
    Gemma 2 is Google’s next-gen open-weight LLM family (notably 9B and 27B) tuned for strong instruction following, reasoning, and coding. It’s efficient, long-context, quantization-friendly, and easy to run locally or on cloud platforms.
    Text
    Released 1y ago
  • Gen 7Gemma
    PaliGemma
    By Google
    PaliGemma is Google’s open-weight vision-language model in the Gemma family. It takes images (or screenshots, documents, charts) plus text and answers in text—great for OCR, captioning, VQA, and UI/doc understanding. Lightweight and fine-tunable, it runs on a single GPU and supports quantization for edge deployment.
    Text
    Released 1y ago
  • Gen 7Gemma
    CodeGemma
    By Google
    CodeGemma is Google’s code-specialized Gemma variant, tuned for software tasks like code generation, completion (incl. fill-in-the-middle), refactoring, debugging, docstring and test creation. It’s efficient, runs on a single GPU or locally with quantization, and supports tool/function calling and structured (JSON) outputs.
    Text
    Released 1y ago
  • Gen 6Gemma
    Gemma 1
    By Google
    Gemma 1 is Google’s lightweight open model family for text generation and chat. It comes in small sizes that run fast on a single GPU or laptop, with instruction-tuned variants for clean following of directions, basic coding, and multilingual tasks.
    Text
    Released 2y ago

No models found

Try adjusting your search or filters.

0 AIs selected
Clear selection
#
Name
Task