Load 4bit models 4x faster - 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

Load 4bit models 4x faster

updated 11 days ago

Native bitsandbytes 4bit pre quantized models