{"model":{"id":"qwen3.8-27b-q8","name":"Qwen3.8 27B (Q8)","quantization":"Q8_0"},"hardware":{"slug":"rtx-4060","name":"NVIDIA GeForce RTX 4060","memoryGb":8},"verdict":"no","localVerdict":"local_unlikely","fitLevel":"Heavy","estimatedLoadGb":27.1,"usableMemoryGb":7.2,"estimatedTokensPerSec":0.7,"kvCacheByContext":[{"contextTokens":8192,"kvGb":0.5,"totalGb":27.6,"fits":false},{"contextTokens":16384,"kvGb":1,"totalGb":28.1,"fits":false},{"contextTokens":32768,"kvGb":2,"totalGb":29.1,"fits":false},{"contextTokens":65536,"kvGb":4,"totalGb":31.1,"fits":false},{"contextTokens":131072,"kvGb":8,"totalGb":35.1,"fits":false}],"upgradeGpu":{"slug":"ryzen-ai-max-395","name":"AMD Ryzen AI Max+ 395 (Strix Halo)"},"ollamaCommand":"ollama run qwen3.8:27b-q8_0","reportUrl":"https://modelfit.io/can-i-run/qwen3.8-27b-q8-on-rtx-4060/","source":"https://modelfit.io/","license":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)","caveat":"Estimates from the ModelFit engine, not measurements."}