Tag
XYZ AI Lab releases XYZ-Aquila-mini, an open-weight thinking model for agentic deep search, fine-tuned from Qwen3.6-35B-A3B, achieving top benchmark scores among sub-40B open-weight models.
XYZ AI Lab releases XYZ-Aquila-pro, an open-weight thinking model for agentic deep search, post-trained from Qwen3.5-397B-A17B via a bounded-exploration AI4AI pipeline, with strong benchmark results in sub-400B open-weight comparisons.
MiniCPM5-1B-Claude-Opus-Fable5-Thinking is a compact 1B thinking language model fine-tuned from openbmb/MiniCPM5-1B on Fable 5 data, enhancing coding and instruction-following while retaining the native thinking chat template and tool-call format. It supports up to 128K context and is suitable for local deployment.
A GGUF quantized version of MiniCPM5-1B-Claude-Opus-Fable5-Thinking model is released on Hugging Face, with usage instructions for llama.cpp, vLLM, and Ollama.
Ring-2.6-1T, a trillion-scale open-source thinking model designed for complex agent tasks, coding, reasoning, and enterprise automation, has been released.
DavidAU releases a fine-tuned version of Qwen 3.5 9B called Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED, using Claude 4.6 distill data to improve reasoning and remove censorship. Benchmarks show improvements over the base model with reduced refusal rates.