Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
unsloth
's Collections
Unsloth Dynamic 2.0 Quants
Gemma 4
Qwen3.5
Unsloth Diffusion GGUFs
Qwen3.6
gpt-oss
Qwen3-Coder
Qwen3-VL
Qwen3
DeepSeek-V3.1
DeepSeek R1 (All Versions)
Embedding Models
Gemma 3
Ministral 3
Granite 4.0
Gemma 3n
Llama 4
Phi-4 (All Versions)
Unsloth 4-bit Dynamic Quants
Deepseek V3 (All Versions)
Text-to-Speech (TTS) models
Mistral Small 3 (All Versions)
Llama 3.2
Llama 3.3 (All Versions)
Qwen2.5-VL (All Versions)
Qwen QwQ-32B Collection
Vision/multimodal Models
Llama 3.2 Vision
Qwen 2.5 Coder
Llama 3.1 Collection
Qwen 2.5
Load 4bit models 4x faster
4bit Instruct Models
Llama 3.3 (All Versions)
updated
2 days ago
Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions.
Upvote
38
+28
unsloth/Llama-3.3-70B-Instruct-GGUF
Text Generation
•
71B
•
Updated
May 10, 2025
•
25.2k
•
104
unsloth/Llama-3.3-70B-Instruct
Text Generation
•
71B
•
Updated
Nov 25, 2025
•
9.94k
•
51
unsloth/Llama-3.3-70B-Instruct-bnb-4bit
Text Generation
•
71B
•
Updated
Nov 25, 2025
•
13k
•
52
Upvote
38
+34
Share collection
View history
Collection guide
Browse collections