🔮Unsloth Model Catalog
Unsloth LLMs directory for all our Dynamic GGUF, 4-bit, 16-bit models on Hugging Face.
QwenDeepSeekGemmaLlamaMistralGLM
GGUFs let you run models in tools like Unsloth Studio✨, Ollama and llama.cpp. Instruct (4-bit) safetensors can be used for inference or fine-tuning via Unsloth.
New & recommended models:
DeepSeek models:
Llama models:
Gemma models:
Qwen models:
GLM models:
Mistral models:
Phi models:
Other (GLM, Orpheus, Smol, Llava etc.) models:
16-bit and 8-bit Instruct models are used for inference or fine-tuning in Unsloth Studio:
New models:
DeepSeek models
Llama models
Gemma models:
Qwen models:
QVQ (preview)
72 B
—
Mistral models:
Phi models:
Text-to-Speech (TTS) models:
Base models are usually used for fine-tuning purposes:
New models:
Llama models:
Qwen models:
Llama models:
Gemma models
Mistral models:
Other (TTS, TinyLlama) models:
You can use our FP8 uploads for training or serving/deployment.
FP8 Dynamic offers slightly faster training and lower VRAM usage than FP8 Block, but with a small trade-off in accuracy.
Last updated
Was this helpful?