Llama 3.3 (All Versions) - a unsloth Collection

unsloth 's Collections

DeepSeek R1 (All Versions)

Unsloth Dynamic 2.0 Quants

Qwen3

Llama 4

Phi-4 (All Versions)

Gemma 3

Unsloth 4-bit Dynamic Quants

Deepseek V3 (All Versions)

Text-to-Speech (TTS) models

Mistral Small 3 (All Versions)

Llama 3.3 (All Versions)

Qwen2.5-VL (All Versions)

Qwen QwQ-32B Collection

Vision/multimodal Models

Llama 3.2 Vision

Llama 3.1 Collection

Load 4bit models 4x faster

4bit Instruct Models

Llama 3.3 (All Versions)

updated 10 days ago

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions.