Run any model, on any backend (Website)

# Run any model,on any backend Source: [https://imvision12.github.io/ZeroModels/](https://imvision12.github.io/ZeroModels/) [NewSAM 3, Gemma 4 and GLM\-5 have landed](https://imvision12.github.io/ZeroModels/sam3/) 100\+ model families ported to pure Keras 3, with weights converted from the original checkpoints\. The same code runs on JAX, PyTorch and TensorFlow, and nothing from`transformers`or`torch`is needed at run time\. ## Two calls to a prediction[¶](https://imvision12.github.io/ZeroModels/#two-calls-to-a-prediction) Build the model with`from\_weights`, then feed it whatever its processor produces\. Every model in the library follows this shape, so moving between a detector, a depth estimator and an LLM costs you nothing\. ``` pip install -U zeromodels ``` Weights come from the[`zeromodels`](https://huggingface.co/zeromodels)org on the Hub, and the same identifier builds both the model and its processor, so the resolution and normalization always match the checkpoint\. ``` import os os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow" from PIL import Image from zeromodels.models.detr import DETRDetect, DETRImageProcessor model = DETRDetect.from_weights("zeromodels/detr-resnet-50") processor = DETRImageProcessor.from_weights("zeromodels/detr-resnet-50") image = Image.open("photo.jpg").convert("RGB") output = model(processor(image)["pixel_values"], training=False) results = processor.post_process_object_detection( output, threshold=0.9, target_sizes=[(image.height, image.width)] )[0] ``` ### One call, three sources[¶](https://imvision12.github.io/ZeroModels/#one-call-three-sources) `from\_weights`dispatches on what you hand it: a preconverted Keras repo on the Hub, a bare variant name that converts an upstream checkpoint on the fly, or any compatible Hugging Face repo behind the`hf:`prefix\. Architecture details, including the class count of a fine\-tune, are read from the repo config\. [Loading weights](https://imvision12.github.io/ZeroModels/loading_weights/)·[Main classes](https://imvision12.github.io/ZeroModels/main_classes/) ``` from zeromodels.models.qwen3 import Qwen3TextGenerate from zeromodels.models.segformer import SegFormerSemanticSegment # Preconverted Keras weights (zm_config.json) SegFormerSemanticSegment.from_weights("zeromodels/segformer_b0_ade_512") # Bare variant: converted from upstream on the fly Qwen3TextGenerate.from_weights("qwen3-8b") # Any Hub repo with a matching model_type SegFormerSemanticSegment.from_weights("hf:nvidia/segformer-b0-finetuned-ade-512-512") # Architecture only, randomly initialized SegFormerSemanticSegment.from_weights( "zeromodels/segformer_b0_ade_512", load_weights=False ) ``` ### Measured outputs, not illustrative ones[¶](https://imvision12.github.io/ZeroModels/#measured-outputs-not-illustrative-ones) Every figure and every printed result on a model page comes from actually running the snippet beside it on the image or audio clip shown\. Nothing is hand\-written to look plausible, so what you read is what you get when you run it yourself\. [Browse the model pages](https://imvision12.github.io/ZeroModels/main_classes/)  ### Any backend, either data format[¶](https://imvision12.github.io/ZeroModels/#any-backend-either-data-format) Set`KERAS\_BACKEND`before importing Keras and the rest is unchanged\. Models read`keras\.config\.image\_data\_format\(\)`when they are**constructed**, so set that first too if you want`channels\_first`; processors take a per\-instance`data\_format`argument\. [Configuration](https://imvision12.github.io/ZeroModels/configuration/)·[Utilities](https://imvision12.github.io/ZeroModels/utils/) ``` import os os.environ["KERAS_BACKEND"] = "jax" # or "torch" / "tensorflow" import keras keras.config.set_image_data_format("channels_first") ``` ### Large checkpoints, as they ship[¶](https://imvision12.github.io/ZeroModels/#large-checkpoints-as-they-ship) - GPT\-OSS 120B loads at bfloat16 with its MoE experts left packed in MXFP4 and dequantized on the fly, so it stays near 66 GB instead of the ~130 GB an fp32 expansion would cost\. - Weight\-only int8, int4, fp8 and mxfp4 are arguments to the same`from\_weights`call, on any model\. [Quantization](https://imvision12.github.io/ZeroModels/quantization/)·[int8](https://imvision12.github.io/ZeroModels/quantization_int8/)·[int4](https://imvision12.github.io/ZeroModels/quantization_int4/)·[fp8](https://imvision12.github.io/ZeroModels/quantization_fp8/)·[mxfp4](https://imvision12.github.io/ZeroModels/quantization_mxfp4/) ``` from zeromodels.models.gpt_oss import GptOssTextGenerate # Experts stay packed in MXFP4, dequantized in the expert layer's call model = GptOssTextGenerate.from_weights("zeromodels/gpt-oss-120b") # Quantize weight-only on the way in, for a smaller footprint again model = GptOssTextGenerate.from_weights("zeromodels/gpt-oss-120b", quantization="int8") ``` ## Where to start[¶](https://imvision12.github.io/ZeroModels/#where-to-start) ## Ready to use ZeroModels? One install, 118 model families, three backends\.