Open-weights 35B MoE (3B active) agentic model from Accio Lab, post-trained from Qwen3.6-35B-A3B.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Occamy 1.0 is an open-weights mixture-of-experts language model from Accio Lab, post-trained from Qwen/Qwen3.6-35B-A3B (about 35B total parameters, 3B active). It is positioned for agentic "co-work" use: tool use, coding and long-context tasks. The Hugging Face card lists an image-text-to-text pipeline, so the BF16 checkpoint accepts text and image input and produces text.
Weights are released under Apache 2.0, and the authors also publish a training framework (Dressage) and a technical report. Many quantized variants are available: GGUF (about 11.66 to 36.90 GB, IQ2_M to Q8_0), APEX GGUF, FP8, NVFP4 and several MLX bit widths. The MLX builds are text-only and the model card notes that Mac Metal acceptance testing is still pending. The BF16 weights are about 70 GB. Runtimes include Transformers, vLLM, SGLang, llama.cpp and mlx-lm.
A YouTube reviewer (AI Search) reported that it leads similarly sized models on agentic benchmarks and competes with some much larger ones. That claim is from a secondary source and was not independently verified here. The model is self-hosted, with no hosted service mentioned in the material provided.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Medium-sized open model, a post-train of a Qwen 35B MoE with 3B active parameters. It tops similar-sized models on agentic benchmarks and competes with some much larger models. Weights and training recipe are open, and the smallest GGUF is about 12 GB.
Closest neighbours by meaning, not just by category.
Model
Open model family (9B dense, 35B MoE, 397B MoE) trained with a self-improvement loop for reasoning, coding and agentic tasks.
Model
35B Mixture-of-Experts open-weights model from InternScience for long-horizon agentic search, engineering and tool use.
Model · MiniMax
Open-weights native multimodal MoE model from MiniMax, ~428B parameters (~23B active) with 1M-token context.
Model · Z.ai
Z.ai's open-weights 753B MoE language model, a post-trained GLM-5.2 aimed at coding, agentic tasks and cybersecurity.
Model · IQuest Lab
320B-parameter MoE model (15B active) from IQuest for agentic coding and tool use, with 512K context.
Model · Alibaba
Alibaba's open-weights 2.4T-parameter MoE language model (95B active) from the Qwen3.8 family, with a hosted Max version.
