This is a list of all available Large Language Models (LLMs) that you can use on your local machine or in a cloud server (via vast.ai
or runpod.io
).
This list is in order from A-Z and from least parameter to most parameter (7B -> 120B).
To differentiate models with the same name, but have different model architectures, their model architecture is listed with the model name itself.
Model Warning
· Running AWQ models require you to use Aphrodite (using-q awq
) or Oobabooga (usingautoAWQ
).
· Running GPTQ models require you to use either Aphrodite (using-q gptq
), KoboldAI or Oobabooga (usingexllama_HF
).
· Running GGUF models require you to use KoboldCPP or Oobabooga (usingllama.cpp
).
This list won't include models that are considered old and/or out of date. If a model you like isn't in the list, it may also be because we simply forgot.
Model Name | Parameter Size | Downloads |
---|---|---|
Pygmalion-2 | 7B | Base, GPTQ, GGUF, AWQ |
13B | Base, GPTQ, GGUF, AWQ | |
Rose | 20B | Base, GPTQ, GGUF, AWQ |
Goliath | 120B | Base, GPTQ, GGUF, AWQ |
Airoboros Mistral 2.2 | 7B | Base, GPTQ, GGUF, AWQ |
Airoboros 2.2.1 | 13B | Base, GPTQ, GGUF, AWQ |
Airoboros 2.2.1 LimaRPv3 | 34B | Base, ExL2 |
Athena v3 | 13B | Base, GPTQ, GGUF, AWQ |
Mistral 7B Claude Chat | 7B | Base, GPTQ, GGUF, AWQ |
Mythalion | 13B | Base, GPTQ, GGUF, AWQ |
MythoMax | 13B | Base, GPTQ, GGUF, AWQ |
Noromaid 0.1.1 | 13B | Base, GPTQ, GGUF, AWQ |
20B | Base, GPTQ, GGUF, AWQ | |
OpenHermes 2.5 Mistral | 7B | Base, GPTQ, GGUF, AWQ |
Orca 2 | 7B | Base, GPTQ, GGUF, AWQ |
13B | Base, GPTQ, GGUF, AWQ | |
PsyFighter2 | 13B | GGUF |
psyonic-cetacean | 20B | Base, GPTQ, GGUF, AWQ, exl2 |
ReMM SLERP | 13B | Base, GPTQ, GGUF, AWQ |
TieFighterLR | 13B | Base, GPTQ, GGUF, AWQ |
Thorns | 13B | Base, GPTQ, GGUF, AWQ |
Zephyr Norobots | 7B | Base, GPTQ, GGUF, AWQ |