GraySoft
Download guIDE →
Model Comparison

ggml-org/embeddinggemma-300m-qat-q8_0-ggufvsunsloth/gemma-4-31b-it-gguf

Side-by-side comparison of ggml-org/embeddinggemma-300m-qat-q8_0-gguf and unsloth/gemma-4-31b-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…

unsloth/gemma-4-31b-it-gguf

unsloth · image-text-to-text

processor = AutoProcessor.from_pretrained(MODEL_ID) model = AutoModelForCausalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto" ) `` Once the model is loaded, you can start generating output: `python # Prompt messages = [ {"role": "system", "content": "You are a help…

Side-by-side Specifications

ggml-org/embeddinggemma-300m-qat-q8_0-ggufunsloth/gemma-4-31b-it-gguf
Authorggml-orgunsloth
Pipeline Taskfeature-extractionimage-text-to-text
Librarysentence-transformers—
Downloads47,8061,362,626
Likes15325
LicenseUnknownUnknown
Context Length——
Created2025-09-042026-04-01
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
ggufgemma4unslothgemmagoogleimage-text-to-textbase_model:google/gemma-4-31B-itbase_model:quantized:google/gemma-4-31B-itlicense:apache-2.0endpoints_compatible

View full details: ggml-org/embeddinggemma-300m-qat-q8_0-gguf · unsloth/gemma-4-31b-it-gguf