Available AIM containers

Available AIM containers#

Cohere Labs#

111B parameter language model with configurable reasoning and tool use capabilities.

Technical specification

Meta Llama#

Multilingual 405B parameter instruction-tuned language model for dialogue use cases.

Technical specification

Multilingual 8B parameter instruction-tuned language model for dialogue use cases.

Technical specification

Multilingual 1B parameter instruction-tuned language model for dialogue and on-device use cases.

Technical specification

Multilingual 3B parameter instruction-tuned language model for dialogue and on-device use cases.

Technical specification

Multilingual 70B parameter instruction-tuned language model for dialogue use cases.

Technical specification

Mistral AI#

14B parameter instruction-tuned language model with vision and function calling capabilities.

Technical specification

14B parameter instruction-tuned language model with vision and function calling capabilities.

Technical specification

675B parameter granular MoE multimodal model with 41B active parameters and vision capabilities.

Technical specification

24B parameter instruction-tuned language model with vision and function calling capabilities.

Technical specification

Sparse MoE language model with 141B total parameters across 8 experts and function calling support.

Technical specification

Sparse MoE language model with 47B total parameters across 8 experts.

Technical specification

OpenAI#

Open-weight 117B parameter MoE model with 5.1B active parameters and configurable reasoning.

Technical specification

Open-weight 21B parameter MoE model with 3.6B active parameters for lower-latency use cases.

Technical specification

Qwen#

235B parameter MoE language model with 22B active parameters and dual thinking modes.

Technical specification

Qwen/Qwen3-32B (stable)

32.8B parameter dense language model with dual thinking modes and multilingual support.

Technical specification

80B parameter MoE coding agent model with 3B active parameters and hybrid attention architecture.

Technical specification

236B parameter MoE vision-language model with 22B active parameters and multimodal capabilities.

Technical specification

236B parameter MoE vision-language model with reasoning-enhanced thinking capabilities.

Technical specification

deepseek-ai#

671B parameter MoE reasoning model with 37B active parameters and 128K context length.

Technical specification

671B parameter MoE reasoning model with 37B active parameters, updated version of DeepSeek-R1.

Technical specification

671B parameter MoE model with 37B active parameters supporting thinking and non-thinking modes.

Technical specification

671B parameter MoE model with 37B active parameters, refined for language consistency and agent tasks.

Technical specification

google#

Gemma 3 27B IT is a multimodal instruction-tuned model supporting text and image input with a 128K context window.

Technical specification