AI Model Catalogue

Open-source qwen3.5-35b-a3b-base-terminal_swe_general-agent-ablation-step7176 model from eewer — available for download and self-hosting on Hugging Face.

Open-source qwen3.5-35b-a3b-base-terminal_swe-agent-ablation-step7073 model from eewer — available for download and self-hosting on Hugging Face.

Open-source react-agent-coder-llama-3.1-8b-GGUF model from smarttasks — available for download and self-hosting on Hugging Face.

Open-source Qwen35B-Agent-R2-Abliterated model from hotdogs — available for download and self-hosting on Hugging Face.

Open-source Qwen35B-Agent-R2 model from hotdogs — available for download and self-hosting on Hugging Face.

Open-source Agents-A1-oQ4e model from basher17 — available for download and self-hosting on Hugging Face.

Open-source Qwen35B-Agent-R2-i1-GGUF model from mradermacher — available for download and self-hosting on Hugging Face.

Open-source Huihui-Agents-A1-abliterated model from spinochenza — available for download and self-hosting on Hugging Face.

Open-source MiniCPM5-1B-Agentic-Tooluse-GGUF model from ewinregirgojr — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF model from franklynical — available for download and self-hosting on Hugging Face.

Open-source Merlin-Agent model from merlin-research — available for download and self-hosting on Hugging Face.

Open-source pc-agent-dispatcher-gemma4-e2b model from onevloth — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-uncensored-heretic-GGUF model from llmfan46 — available for download and self-hosting on Hugging Face.

Open-source Uraion-Agent-Steer model from uraionlabs — available for download and self-hosting on Hugging Face.

Open-source Agents-A1-AutoRound-W4A16-RTN model from leaderboardmodel1 — available for download and self-hosting on Hugging Face.

Open-source Uraion-Agent-Small model from uraionlabs — available for download and self-hosting on Hugging Face.

Open-source Agent-Nemotron-ROCmFP6 model from cafonez — available for download and self-hosting on Hugging Face.

Open-source Qwen3.6-35B-A3B-REAM-160-ru-agent-VLM-MLX-mixed-3-6 model from wavecut — available for download and self-hosting on Hugging Face.

Open-source Qwen3.6-35B-A3B-REAM-160-ru-agent-VLM-MLX-mixed-4-6 model from wavecut — available for download and self-hosting on Hugging Face.

Open-source Qwen3.6-35B-A3B-REAM-160-ru-agent-VLM-MLX-MXFP4-router8 model from wavecut — available for download and self-hosting on Hugging Face.

Open-source Qwen3.6-35B-A3B-REAM-160-ru-agent-VLM-MLX-4bit model from wavecut — available for download and self-hosting on Hugging Face.

Open-source gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF model from claymorecrystal — available for download and self-hosting on Hugging Face.

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Kimi K2.5 is a frontier-scale open-source model with a 256k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.

Flux is the first conversational speech recognition model built specifically for voice agents.

Granite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. These efficiencies make the models well-suited for a wide range of use cases like retrieval-augmented generation (RAG), multi-agent workflows, and edge deployments.

NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.

Kimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...