| model | inference | size | quantized link |
|---|---|---|---|
| Llama2 | LLaMA | 7B | huggingface |
| OpenLLaMa v2 | LLaMA | 3B | huggingface |
| ORCA | LLaMA | 3B | huggingface |
| ORCA v3 | LLaMA | 7B | huggingface |
| Marx v2 | LLaMA | 3B | huggingface |
| RWKV 4 Raven | RWKV | 3B | huggingface |
| StableLM-3B-4E1T | GPT-NeoX | 3B | huggingface |
| Pythia | GPT-NeoX | 2.8B | huggingface |
| Cerebras | GPT-2 | 1.3B | huggingface |
| MagicPrompt SDiffusion | GPT-2 | 111M | huggingface |
| Replit | Replit | 3B | huggingface |
| Santacoder | Starcoder | 1B | huggingface |
| MPT-7B-StoryWriter-65k+ | MTP | 7B | huggingface |
| Bloomz | Bloom | 1.7B | huggingface |