Model Catalog
Ready-to-use configurations for
1-click deployments!
Llama-3.1-8B-Instruct
An 8-billion parameter model from Meta, optimized for dialogue. Generates helpful, safe responses and outperforms other open-source chat LLMs.
Llama-3.1-70B-Instruct
A 70-billion parameter model from Meta, optimized for dialogue. Generates helpful, safe responses and outperforms other open-source chat LLMs.
gemma-2-9b-it
An instruction model fine-tuned from Gemma 2, Google's open LLM. This version has 9 billion parameters.
gemma-2-27b-it
An instruction model fine-tuned from Gemma 2, Google's open LLM. This version has 27 billion parameters.
Qwen2-7B-Instruct
Powerful multilingual instruction-tuned 7B model from Qwen, supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs.
Qwen2-72B-Instruct
Powerful multilingual instruction-tuned 72B model from Qwen, supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs.
Qwen2.5-Coder-7B-Instruct
Instruction-tuned 7B model for code generation, code reasoning and code fixing from Qwen, supports a context length of up to 128K tokens.
OpenHermes-2.5-Mistral-7B-GPTQ
A powerful chat model fine-tuned from Mistral 7B on a large corpus of synthetic data. Capable of function-calling and has strong coding capabilities.
NeuralHermes-2.5-Mistral-7B-GPTQ
A fine-tuned version of OpenHermes 2.5 that was aligned with Direct Preference Optimization and AI preference examples from the SlimOrca dataset.
Starling-LM-7B-alpha
Open chat language model by UC Berkeley. Outperformed all 7B models at the time of its release. For non-commercial use only.
openchat-3.5-0106
Open source LLM that targets high performance and commercial viability. Fine-tuned using C-RLFT, for results on par with ChatGPT.
Mistral-Nemo-Instruct-2407
Instruct fine-tuned version trained jointly by Mistral AI and NVIDIA. Significantly outperforms existing models similar in size.
zephyr-7b-beta
A chat model fine-tuned from Mistral 7B with synthetic data and Direct Preference Optimization.
neural-chat-7b-v3-1
A chat model from Intel, fine-tuned from Mistral 7B on the SlimOrca dataset with Direct Preference Optimization.
Falcon-180B-Chat-GPTQ
A 180-billion parameter conversational AI model optimized for fast inference through an efficient architecture. Freely available under TII LICENSE.
Mixtral-8x7B-Instruct-v0.1
Mixtral 8x7B is a sparse mixture-of-experts decoder-only model fine-tuned on instruction following a permissive license.