Available AIM containers#

Instinct#

Cohere Labs#

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

Technical specification

DeepSeek#

671B parameter MoE reasoning model with 37B active parameters.

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 1B IT is a lightweight instruction-tuned model supporting text generation with a 32K context window.

Technical specification

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

Technical specification

Gemma 4 31B IT is a multimodal instruction-tuned model with text and image input, 256K native context, and Gemma 4 reasoning + tool-call parsers.

Technical specification

Gemma 3-based 27B multimodal model fine-tuned for medical text and image tasks (X-ray, dermatology, ophthalmology, pathology, radiology reports).

Technical specification

Meta#

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

MiniMax#

228B parameter mixture-of-experts language model with reasoning, tool calling, and coding capabilities.

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 (Mistral Small 3) with native function calling. Text-only.

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

Z.ai#

zai-org/GLM-4.7 (stable)

GLM-4.7 is a large language model with multi-turn conversation, tool use, and reasoning capabilities.

Technical specification

EPYC#

Google#

Gemma 4 E4B is Google’s efficient instruction-tuned model with a ~4B effective-parameter MatFormer architecture for low-latency on-device and CPU inference.

Technical specification

Meta#

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

Qwen#

Mixture-of-experts 30B (3B active) LLM with thinking/non-thinking mode switching, advanced reasoning, agent capabilities, and 100+ language support.

Technical specification

Qwen/Qwen3-8B (stable)

Reasoning-enhanced 8B parameter LLM with thinking/non-thinking mode switching, excelling in math, coding, and multi-turn conversations.

Technical specification

Qwen/Qwen3.5-4B (stable)

Qwen3.5-4B is a 4B parameter LLM with thinking/non-thinking dual-mode reasoning, strong math and coding ability, and multilingual support.

Technical specification

Qwen/Qwen3.5-9B (stable)

Qwen3.5-9B is a 9B parameter LLM with thinking/non-thinking dual-mode reasoning, strong math and coding ability, and multilingual support.

Technical specification

Qwen3.6-35B-A3B is a Mixture-of-Experts LLM with 35B total parameters and ~3B active per token, balancing high quality with efficient inference.

Technical specification

unsloth#

gpt-oss-20B is OpenAI’s open-weight 20B Mixture-of-Experts model (BF16 conversion by Unsloth) with strong reasoning and tool-use capabilities.

Technical specification

Radeon#

Google#

Gemma 3n E4B IT is a gated multimodal instruction-tuned model supporting text, image, video, and audio inputs.

Technical specification

Meta#

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

Technical specification

Qwen#

8B parameter vision-language model with advanced multimodal reasoning.

Technical specification

Qwen/Qwen3.5-9B (preview)

9B parameter hybrid language model with Gated DeltaNet and dual thinking modes.

Technical specification

Z.ai#

30B-A3B MoE language model with balanced performance and efficiency for lightweight deployment.

Technical specification