Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled — UD 2.0 GGUF Unsloth Dynamic 2.0 (UD) GGUF quants of hesamation/Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled . UD 2.0 recipes extracted from unsloth/Qwen3.6 35B A3B GGUF imatrix from the same repo Per tensor quant overrides applied via stock llama.cpp 's tensor type Recommended quants Quant Approx size Notes UD Q4 K XL best quality/size ratio for most users recommended default UD Q5 K M higher quality if you have headroom UD Q3 K XL smaller, still very usable tight VRAM UD Q2 K XL extreme compression budget setups Files appear here as they finish quantizing. See the file list below. Run with llama.cpp From original model: 🔥 Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled A reasoning SFT fine tune of Qwen/Qwen3.6 35B A3B on chain of thought (CoT) distillation mostly sourced from Claude Opus 4.6. The goal is to preserve Qwen3.6's strong agentic coding and reasoning base while nudging the model toward structured Claude Opus style reasoning traces and more stable long form problem solving. The training path is text only. The Qwen3.6 base architecture includes a vision encoder, but this fine tuning run did not train on ima…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy