Gemma Instruct (2B)

2B instruct Gemma model by Google: lightweight, open, text-to-text LLM for QA, summarization, reasoning, and resource-efficient deployment.

Try this model
Llama 3.2 3B Instruct Turbo

Multimodal LLM optimized for visual recognition, image reasoning, captioning, and answering image-related questions.

Try this model
DBRX-Instruct

MoE LLM trained from scratch and specialized in few-turn interactions for enhanced performance.

Try this model
Gemma 3 12B

Lightweight Gemma 3 model with 128K context, vision-language input, and multilingual support for on-device AI.

Try this model
Gemma 3 4B

Lightweight Gemma 3 model (1B) with 128K context, vision-language input, and multilingual support for on-device AI.

Try this model
Gemma 3 1B

Most lightweight Gemma 3 model, with 128K context, vision-language input, and multilingual support for on-device AI.

Try this model
DeepSeek R1 Distilled Qwen 1.5B

Small Qwen 1.5B distilled with reasoning capabilities from Deepseek R1. Beats GPT-4o on MATH-500 whilst being a fraction of the size.

Try this model
DeepSeek R1 Distilled Qwen 14B

Qwen 14B distilled with reasoning capabilities from Deepseek R1. Outperforms GPT-4o in math & matches o1-mini on coding.

Try this model
DeepSeek R1 Distilled Llama 70B

Llama 70B distilled with reasoning capabilities from Deepseek R1. Surpasses GPT-4o with 94.5% on MATH-500 & matches o1-mini on coding.

Try this model
Llama 3.1 8B

Multilingual LLM pre-trained and instruction-tuned, surpassing open and closed models on key benchmarks.

Try this model
Gemma-2 Instruct (27B)

Lightweight, SOTA open models from Google, leveraging research and tech behind the Gemini models.

Try this model
Llama 3.1 405B

Multilingual LLM pre-trained and instruction-tuned, surpassing open and closed models on key benchmarks.

Try this model
Llama 3.3 70B

70B multilingual LLM, pretrained and instruction-tuned, excels in dialogue use cases, surpassing open and closed models.

Try this model
Cogito V1 Preview Llama 3B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.

Try this model
Llama 3.1 Nemotron 70B Instruct

Custom NVIDIA LLM optimized to enhance the helpfulness and relevance of generated responses to user queries.

Try this model
Cogito V1 Preview Llama 8B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.

Try this model
Mistral Small 3

24B model rivaling GPT-4o mini, and larger models like Llama 3.3 70B. Ideal for chat use cases like customer support, translation and summarization.

Try this model
Cogito V1 Preview Qwen 14B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.

Try this model
Qwen2.5 72B

Decoder-only model built for advanced language processing tasks.

Try this model
Cogito V1 Preview Qwen 32B

Best-in-class open-source LLM trained with IDA for alignment, reasoning, and self-reflective, agentic applications.

Try this model

Let's stay in touch.

Get Contact
cta-area