GraySoft
Download guIDE →
Model Comparison

ggml-org/qwen3-reranker-0.6b-q8_0-ggufvsunsloth/ministral-3-14b-reasoning-2512-gguf

Side-by-side comparison of ggml-org/qwen3-reranker-0.6b-q8_0-gguf and unsloth/ministral-3-14b-reasoning-2512-gguf: downloads, license, context length, tasks, and benchmarks.

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.

unsloth/ministral-3-14b-reasoning-2512-gguf

unsloth · —

The largest model in the Ministral 3 family, **Ministral 3 14B** offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities. This model is the reasoning post-trained ve…

Side-by-side Specifications

ggml-org/qwen3-reranker-0.6b-q8_0-ggufunsloth/ministral-3-14b-reasoning-2512-gguf
Authorggml-orgunsloth
Pipeline Tasktext-ranking—
Librarytransformersvllm
Downloads33,06120,972
Likes1444
LicenseUnknownUnknown
Context Length——
Created2025-10-032025-12-02
Last Modified2025-10-032025-12-04
Tags
transformersggufllama-cppgguf-my-repotext-rankingbase_model:Qwen/Qwen3-Reranker-0.6Bbase_model:quantized:Qwen/Qwen3-Reranker-0.6Blicense:apache-2.0endpoints_compatibleregion:us
vllmggufmistral-commonmistralunslothenfresdeit

View full details: ggml-org/qwen3-reranker-0.6b-q8_0-gguf · unsloth/ministral-3-14b-reasoning-2512-gguf