Llamacpp imatrix Quantizations of Hermes 3 Llama 3.2 3B Using llama.cpp release b4273 for quantization. Original model: https://huggingface.co/NousResearch/Hermes 3 Llama 3.2 3B All quants made using imatrix option with dataset from here Run them in LM Studio Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Hermes 3 Llama 3.2 3B f32.gguf f32 12.86GB false Full F32 weights. Hermes 3 Llama 3.2 3B f16.gguf f16 6.43GB false Full F16 weights. Hermes 3 Llama 3.2 3B Q8 0.gguf Q8 0 3.42GB false Extremely high quality, generally unneeded but max available quant. Hermes 3 Llama 3.2 3B Q6 K L.gguf Q6 K L 2.74GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Hermes 3 Llama 3.2 3B Q6 K.gguf Q6 K 2.64GB false Very high quality, near perfect, recommended . Hermes 3 Llama 3.2 3B Q5 K L.gguf Q5 K L 2.42GB false Uses Q8 0 for embed and output weights. High quality, recommended . Hermes 3 Llama 3.2 3B Q5 K M.gguf Q5 K M 2.32GB false High quality, recommended . Hermes 3 Llama 3.2 3B Q5 K S.gguf Q5 K S 2.27GB false High quality, recommended . Hermes 3 Llama 3.2 3B Q4 K L.gguf Q4 K L 2.11GB fals…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy