Llamacpp imatrix Quantizations of Llama 3.3 8B Instruct by allura forge Using llama.cpp release b7545 for quantization. Original model: https://huggingface.co/allura forge/Llama 3.3 8B Instruct All quants made using imatrix option with dataset from here combined with a subset of combined all small.parquet from Ed Addario here Run them in your choice of tools: llama.cpp LM Studio koboldcpp Jan AI Text Generation Web UI LoLLMs Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description Llama 3.3 8B Instruct bf16.gguf bf16 16.07GB false Full BF16 weights. Llama 3.3 8B Instruct Q8 0.gguf Q8 0 8.54GB false Extremely high quality, generally unneeded but max available quant. Llama 3.3 8B Instruct Q6 K L.gguf Q6 K L 6.85GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . Llama 3.3 8B Instruct Q6 K.gguf Q6 K 6.60GB false Very high quality, near perfect, recommended . Llama 3.3 8B Instruct Q5 K L.gguf Q5 K L 6.06GB false Uses Q8 0 for embed and output weights. High quality, recommended . Llama 3.3 8B Instruct Q5 K M.gguf Q5 K M 5.73GB false High quality, recommended . Llama 3.3 8B Instruct Q5 K S…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy