AI Model Catalogue

Meta's Llama 3.1 8B served on Groq's LPU for ultra-low latency — ideal for fast, lightweight text tasks.

OpenAI's Whisper Large v3 served on Groq for fast, accurate speech-to-text transcription.

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Meta's Llama 3.3 70B — latest iteration with improved instruction following, served on Groq LPU.

Groq-optimised Whisper Large v3 Turbo — fastest ASR with accuracy comparable to Whisper v3.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...