analyzing 37 models temperature: 0.9 num_ctx: 2048 prompt: updating model: qwen2:7b-instruct-q8_0 pulling manifest pulling 8c3c7010ad6e pulling 62fbfd9ed093 pulling c156170b718e pulling f02dd72bb242 pulling a649b68e50e7 verifying sha256 digest writing manifest removing any unused layers success loading model: qwen2:7b-instruct-q8_0 size: 7723M par: 7.6B fam: qwen2 parameter_size: 7.6B quantization_level: Q8_0 template: parameters: random check: 7E 16 EE 6D C0 A9 FE ED 61 4B