GraySoft
Model Comparison

ggml-org/embeddinggemma-300m-qat-q8_0-ggufvsmradermacher/apertus-70b-instruct-2509-heretic-v2-i1-gguf

Side-by-side comparison of ggml-org/embeddinggemma-300m-qat-q8_0-gguf and mradermacher/apertus-70b-instruct-2509-heretic-v2-i1-gguf: downloads, license, context length, tasks, and benchmarks.

ggml-org/embeddinggemma-300m-qat-q8_0-gguf

ggml-org · feature-extraction

# embeddinggemma-300m-qat-q8_0 GGUF Recommended way to run this model: ``sh llama-server -hf ggml-org/embeddinggemma-300m-qat-q8_0-GGUF --embeddings ` Then the endpoint can be accessed at http://localhost:8080/embedding, for example using curl: `console curl --request POST \ --u…

mradermacher/apertus-70b-instruct-2509-heretic-v2-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/surelio/Apertus-70B-Instruct-2509-heretic-v1.1.2 ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Apertus-70B-Inst…

Side-by-side Specifications

ggml-org/embeddinggemma-300m-qat-q8_0-ggufmradermacher/apertus-70b-instruct-2509-heretic-v2-i1-gguf
Authorggml-orgmradermacher
Pipeline Taskfeature-extraction
Librarysentence-transformerstransformers
Downloads47,80627,670
Likes150
LicenseUnknownUnknown
Context Length
Created2025-09-042026-04-02
Last Modified2025-09-152026-04-11
Tags
sentence-transformersggufsentence-similarityfeature-extractionbase_model:google/embeddinggemma-300m-qat-q8_0-unquantizedbase_model:quantized:google/embeddinggemma-300m-qat-q8_0-unquantizedlicense:gemmaendpoints_compatibleregion:us
transformersggufmultilingualcompliantswiss-aiapertushereticuncensoreddecensoredabliterated

View full details: ggml-org/embeddinggemma-300m-qat-q8_0-gguf · mradermacher/apertus-70b-instruct-2509-heretic-v2-i1-gguf