GraySoft
Download guIDE →
Model Comparison

bartowski/qwen_qwen3.5-35b-a3b-ggufvsunsloth/llama-3.2-3b-instruct-gguf

Side-by-side comparison of bartowski/qwen_qwen3.5-35b-a3b-gguf and unsloth/llama-3.2-3b-instruct-gguf: downloads, license, context length, tasks, and benchmarks.

bartowski/qwen_qwen3.5-35b-a3b-gguf

bartowski · image-text-to-text

unsloth/llama-3.2-3b-instruct-gguf

unsloth · text-generation

16bit, 8bit, 6bit, 5bit, 4bit, 3bit and 2bit uploads avaliable. # Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth! We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXH…

Side-by-side Specifications

bartowski/qwen_qwen3.5-35b-a3b-ggufunsloth/llama-3.2-3b-instruct-gguf
Authorbartowskiunsloth
Pipeline Taskimage-text-to-texttext-generation
Library—transformers
Downloads327,81446,356
Likes6260
LicenseUnknownUnknown
Context Length——
Created2026-02-242024-09-25
Last Modified2026-03-062025-11-08
Tags
ggufimage-text-to-textbase_model:Qwen/Qwen3.5-35B-A3Bbase_model:quantized:Qwen/Qwen3.5-35B-A3Blicense:apache-2.0endpoints_compatibleregion:usimatrixconversational
transformersggufllamatext-generationllama-3metafacebookunslothenbase_model:meta-llama/Llama-3.2-3B-Instruct

View full details: bartowski/qwen_qwen3.5-35b-a3b-gguf · unsloth/llama-3.2-3b-instruct-gguf