Llamacpp imatrix Quantizations of Qwen3.6 35B A3B Anko by allura org Using llama.cpp release b8860 for quantization. Original model: https://huggingface.co/allura org/Qwen3.6 35B A3B Anko All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp ramalama LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Qwen3.6 35B A3B Anko bf16.gguf bf16 69.38GB true Full BF16 weights. Qwen3.6 35B A3B Anko Q8 0.gguf Q8 0 36.91GB false Extremely high quality, generally unneeded but max available quant. Qwen3.6 35B A3B Anko Q6 K L.gguf Q6 K L 30.30GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Qwen3.6 35B A3B Anko Q6 K.gguf Q6 K 30.05GB false Very high quality, near perfect, recommended . Qwen3.6 35B A3B Anko Q5 K L.gguf Q5 K L 25.33GB false Uses Q8 0 for embed and output weights. High quality, recommended . Qwen3.6 35B A3B Anko Q5 K M.gguf Q5 K M 25.02GB false High quality, recommended . Qwen3.…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy