+ Technical Report + Responsible Generative AI Toolkit + TranslateGemma on Kaggle + TranslateGemma on Vertex Model Garden **Terms of Use**: Terms **Authors**: Google Translate TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art translation models and helping foster innovation for everyone.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗You need to download both a high-noise model and a low-noise model. High noise is used for the first steps and the low-noise for the details. Place them on ComfyUI/models/unet You will need ComfyUI-GGUF from city96 💜 Wan    ｜    🖥️ GitHub    |   🤗 Hugging Face    |   🤖 ModelScope    |    📑 Technical Report    |    📑 Blog    |   💬 WeChat Group    |    📖 Discord   
Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗You need to download both a high-noise model and a low-noise model. High noise is used for the first steps and the low-noise for the details. Place them on ComfyUI/models/unet You will need ComfyUI-GGUF from city96 💜 Wan    ｜    🖥️ GitHub    |   🤗 Hugging Face    |   🤖 ModelScope    |    📑 Technical Report    |    📑 Blog    |   💬 WeChat Group    |    📖 Discord   
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Text-only AWQ quantum Qwen3.5-4B (2.91 GiB / 3.13 GB, one safetensors file) with tensors renamed to the flat naming scheme expected by vLLM. The original checkpoint kumar2235/Qwen3.5-4B-AWQ is preserved in the VLM model markup: all tensors are prefixed with `model.language_model.*` (a legacy of `Qwen3_5ForConditionalGeneration`). The vLLM implementation of the text architecture `Qwen3_5ForCausalLM` is flat: expects `model.layers.*`, `model.embed_tokens`, and `model.norm`. Because of this, vLLM doesn't load the original and crashes on startup: Renaming is rewriting the safetensors header (stdlib Python, no dependencies: `data_offsets` in safetensors are calculated from the start of the data section, so the header can be changed freely, the data is not shifted):
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2087 - Precision Macro: 0.9395 - Recall Macro: 0.9394 - F1 Macro: 0.9394 - F1 Neutral: 0.9398 - F1 Toxic: 0.9390 The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗~14T param, 114 layers, hybrid GDN/MLA, MoE (1,224 experts, top-48 + 1 shared), NVFP4. Internal codename `numbat`, Anthropic's next Mythos-class training run. `numbat` is the codename referenced in the Claude Code source leak (Mar 2026). This is a checkpoint from that training run, pulled mid-pretraining. The 772 shards total ~7.72 TB of tensor data. Each shard is safetensors format, under 10.6 GB per file. `configuration_numbat.py` and `modeling_numbat.py` are included: a complete reference implementation of the checkpoint. Its module tree has an exact slot for every tensor in every shard, so the full checkpoint loads with `load_state_dict(strict=True)` (and, since the classes derive from `PreTrainedModel`, also via `AutoModelForCausalLM.from_pretrained(..., trust_remote_code=True)`). `NumbatForCausalLM.forward` runs the trunk and `NumbatForCausalLM.draft` runs the MTP layer.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗