{"verdict":"no","receipt":"https://fitllm.run/r/glm-4-7-flash-8bit-on-mac-32gb","model":"GLM-4.7-Flash","hardware":"Mac 32GB","quant":"8-bit","kvBits":16,"ctx":8192,"structuralAssumptions":[{"id":"mla-compressed-latent-cache","statement":"KV memory assumes a compressed-latent MLA artifact or mode; legacy non-MLA GGUF or an explicitly uncompressed mode invalidates this estimate."}],"memory":{"usedGB":41.76,"totalGB":32,"freeGB":-9.76,"breakdown":{"weightsGB":29.06,"kvCacheGB":0.41,"overheadGB":3.79,"reserveGB":8.5}},"maxContext":0,"contextLimits":{"recommendedMax":0,"hardLimit":0,"headroomPct":20},"fix":"Drop the weights to 4-bit and it fits (KV unchanged).","note":"usedGB = total required to run: weights + KV cache + runtime overhead + OS/GPU reserve. Runtime resident-weights measurements (e.g. oMLX actual_size) read lower — a different metric, not a prediction error.","source":"https://fitllm.run","engine":"fitllm-engine (MIT)","data":"https://fitllm.run/data (CC0)"}