Load 4bit models 4x faster - a unsloth Collection

unsloth 's Collections

Qwen3

Unsloth Dynamic 2.0 Quants

Llama 4

Phi-4 (All Versions)

Gemma 3

Unsloth 4-bit Dynamic Quants

Deepseek V3 (All Versions)

Text-to-Speech (TTS) models

DeepSeek R1 (All Versions)

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

Load 4bit models 4x faster

updated 3 days ago

Native bitsandbytes 4bit pre quantized models