Llamacpp imatrix Quantizations of command a plus 05 2026 by CohereLabs Using llama.cpp release b9626 for quantization. Original model: https://huggingface.co/CohereLabs/command a plus 05 2026 bf16 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 Atomic Chat Note: if it's a newly supported model, you may need to wait for an update from the developers. Prompt format json [ ] Download a file (not the whole branch) from below: Filename Quant type File Size Split Description command a plus 05 2026 Q8 0.gguf Q8 0 231.96GB true Extremely high quality, generally unneeded but max available quant. command a plus 05 2026 Q6 K.gguf Q6 K 189.83GB true Very high quality, near perfect, recommended . command a plus 05 2026 Q5 K M.gguf Q5 K M 157.77GB true High quality, recommended . command a plus 05 2026 Q5 K S.gguf Q5 K S 152.14GB true High quality, recommended . command a plus 05 2026 Q4 1.gguf Q4 1 138.83GB true Legacy format, similar performance to Q4 K S but with improved tokens/watt on Apple silicon. command a plus 05 2026 Q4 K L.gguf Q4 K L 135.35GB true Uses Q8 0 for em…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy