Llamacpp imatrix Quantizations of Qwen3.5 0.8B by Qwen Using llama.cpp release b9222 for quantization. Original model: https://huggingface.co/Qwen/Qwen3.5 0.8B 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 What's new: Adding MTP layers now that support has been added with release b9180 In order to use it, run: Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Qwen3.5 0.8B bf16.gguf bf16 1.56GB false Full BF16 weights. Qwen3.5 0.8B Q8 0.gguf Q8 0 0.84GB false Extremely high quality, generally unneeded but max available quant. Qwen3.5 0.8B Q6 K L.gguf Q6 K L 0.75GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Qwen3.5 0.8B Q5 K L.gguf Q5 K L 0.71GB false Uses Q8 0 for embed and output weights. High quality, recommended . Qwen3.5 0.8B Q6 K.gguf Q6 K 0.69GB false Very high quality, near perfect, recommended . Qwen3.5 0.8B Q5 K M.gguf Q5 K M 0.65GB false High qual…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy