Llamacpp imatrix Quantizations of GLM 4.7 Flash by zai org Using llama.cpp release b7779 for quantization. Original model: https://huggingface.co/zai org/GLM 4.7 Flash All quants made using imatrix option with dataset from here Run them in your choice of tools: llama.cpp 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. It's suggested you disable flash attention ( flash attn off ) for improved performance Re uploaded with fixed imatrix from the fixed gating function: https://github.com/ggml org/llama.cpp/pull/18980 You'll need the updated llama.cpp to get proper output Prompt format Download a file (not the whole branch) from below: Filename Quant type File Size Split Description GLM 4.7 Flash bf16.gguf bf16 59.91GB true Full BF16 weights. GLM 4.7 Flash Q8 0.gguf Q8 0 31.84GB false Extremely high quality, generally unneeded but max available quant. GLM 4.7 Flash Q6 K L.gguf Q6 K L 24.98GB false Uses Q8 0 for embed and output weights. Very high quality, near perfect, recommended . GLM 4.7 Flash Q6 K.gguf Q6 K 24.83GB false Very high quality, near perfect, recommended . GLM 4.7 Flash…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy