Apple Metal (GPU Acceleration on) + use_mlock = off

apple-silicon.preset.json

{
  "name": "Apple Silicon",
  "load_params": {
    "n_ctx": 2048,
    "n_batch": 512,
    "rope_freq_base": 10000,
    "rope_freq_scale": 1,
    "n_gpu_layers": 1,
    "use_mlock": false,
    "main_gpu": 0,
    "tensor_split": [
      0
    ],
    "seed": -1,
    "f16_kv": true,
    "use_mmap": true
  },
  "inference_params": {
    "n_threads": 4,
    "n_predict": -1,
    "top_k": 40,
    "top_p": 0.95,
    "temp": 0.8,
    "repeat_penalty": 1.1,
    "input_prefix": "### Instruction:\n",
    "input_suffix": "\n### Response:\n",
    "antiprompt": [
      "### Instruction:"
    ],
    "pre_prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.",
    "seed": -1,
    "tfs_z": 1,
    "typical_p": 1,
    "repeat_last_n": 64,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "n_keep": 0,
    "logit_bias": {},
    "mirostat": 0,
    "mirostat_tau": 5,
    "mirostat_eta": 0.1,
    "memory_f16": true,
    "multiline_input": false,
    "penalize_nl": true,
    "pre_prompt_prefix": "",
    "pre_prompt_suffix": "\n"
  }
}