INT8 weight-only quantization of google/gemma-4-E4B-it in the compressed-tensors format, ready for vLLM. Text, image and audio inputs are supported as in the original: only the text decoder is quantized. - Per-Layer Embeddings (embedtokensperlayer, perlayerinputgate, perlayerprojection, perlayermodelprojection) - Multimodal projections (embedvision, embedaudio) - Token embeddings and lmhead A large part of the E4B checkpoint is Per-Layer Embeddings, which stay in bf16, so the size reduction is smaller than the "8-bit" label suggests. The full recipe is in recipe.yaml. Perplexity and top-1 next-token agreement against the bf16 original on Wikipedia (wikimedia/wikipedia, dump 20231101)…
Independent publisher
Kozhonv
Bekten
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Any to any.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.