GraySoft
Download guIDE →
Model Comparison

ccssne/gemma-4-31b-it-heretic-ara-ggufvsggml-org/qwen3-reranker-0.6b-q8_0-gguf

Side-by-side comparison of ccssne/gemma-4-31b-it-heretic-ara-gguf and ggml-org/qwen3-reranker-0.6b-q8_0-gguf: downloads, license, context length, tasks, and benchmarks.

ccssne/gemma-4-31b-it-heretic-ara-gguf

CCSSNE · —

# Gemma-4-31B-It-Heretic-GGUF Quantized using Unsloth on RTX 4070 Laptop . This version includes the vision adapter (mmproj) and is optimized for local inference.

ggml-org/qwen3-reranker-0.6b-q8_0-gguf

ggml-org · text-ranking

This model was converted to GGUF format from Qwen/Qwen3-Reranker-0.6B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Side-by-side Specifications

ccssne/gemma-4-31b-it-heretic-ara-ggufggml-org/qwen3-reranker-0.6b-q8_0-gguf
AuthorCCSSNEggml-org
Pipeline Task—text-ranking
Librarygguftransformers
Downloads48,71433,061
Likes414
LicenseUnknownUnknown
Context Length——
Created2026-04-032025-10-03
Last Modified2026-04-032025-10-03
Tags
ggufunslothgemma-4quantizedbase_model:trohrbaugh/gemma-4-31b-it-heretic-arabase_model:quantized:trohrbaugh/gemma-4-31b-it-heretic-araendpoints_compatibleregion:usconversational
transformersggufllama-cppgguf-my-repotext-rankingbase_model:Qwen/Qwen3-Reranker-0.6Bbase_model:quantized:Qwen/Qwen3-Reranker-0.6Blicense:apache-2.0endpoints_compatibleregion:us

View full details: ccssne/gemma-4-31b-it-heretic-ara-gguf · ggml-org/qwen3-reranker-0.6b-q8_0-gguf