GraySoft
Model Comparison

ggml-org/embeddinggemma-300m-qat-q8_0-ggufvsjackrong/gemopus-4-26b-a4b-it-gguf

Side-by-side comparison of ggml-org/embeddinggemma-300m-qat-q8_0-gguf and jackrong/gemopus-4-26b-a4b-it-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…

jackrong/gemopus-4-26b-a4b-it-gguf

Jackrong · text-generation

> [!NOTE] > **Gemopus** is an attempt at fine-tuning Gemma 4 with a core philosophy of "stability first". > > While preserving the original reasoning order of **Gemma 4** as much as possible, we conducted targeted refinements for answer quality, structure, clarity, and consisten…

Side-by-side Specifications

ggml-org/embeddinggemma-300m-qat-q8_0-ggufjackrong/gemopus-4-26b-a4b-it-gguf
Authorggml-orgJackrong
Pipeline Taskfeature-extractiontext-generation
Librarysentence-transformers
Downloads47,80632,243
Likes1576
LicenseUnknownUnknown
Context Length
Created2025-09-042026-04-09
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
ggufgemma4gemmainstruction-tunedreasoningalignmenttext-generationenzhko

View full details: ggml-org/embeddinggemma-300m-qat-q8_0-gguf · jackrong/gemopus-4-26b-a4b-it-gguf