ReactNativeLLM/mlc-config.json at main · Arunkumarvallal/ReactNativeLLM · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
{
  "iphone": [
    {
      "model": "HF://mlc-ai/gemma-2-2b-it-q4f16_1-MLC",
      "model_id": "gemma-2-2b-it-q4f16_1-MLC",
      "estimated_vram_bytes": 30000000,
      "overrides": {
        "context_window_size": 2000,
        "prefill_chunk_size": 125
      }
    },
    {
      "model": "HF://mlc-ai/Llama-3.2-3B-Instruct-q4f16_0-MLC",
      "estimated_vram_bytes": 46799794,
      "model_id": "Llama-3.2-3B-Instruct-q4f16_0-MLC",
      "overrides": {
        "context_window_size": 2000,
        "prefill_chunk_size": 125
      }
    },
    {
      "model": "HF://mlc-ai/Qwen2.5-0.5B-Instruct-q0f16-MLC",
      "model_id": "Qwen2.5-0.5B-Instruct-q0f16-MLC",
      "estimated_vram_bytes": 43000000,
      "bundle_weight": false,
      "overrides": {
        "context_window_size": 2000,
        "prefill_chunk_size": 128
      }
    }

  ],
  "android": [
    {
      "model": "HF://mlc-ai/gemma-2-2b-it-q4f16_1-MLC",
      "model_id": "gemma-2-2b-it-q4f16_1-MLC",
      "estimated_vram_bytes": 30000000
    },
    {
      "model": "HF://mlc-ai/Llama-3.2-3B-Instruct-q4f16_0-MLC",
      "estimated_vram_bytes": 46799794,
      "model_id": "Llama-3.2-3B-Instruct-q4f16_0-MLC"
    },
    {
      "model": "HF://mlc-ai/Qwen2.5-0.5B-Instruct-q0f16-MLC",
      "model_id": "Qwen2.5-0.5B-Instruct-q0f16-MLC",
      "estimated_vram_bytes": 43000000,
      "bundle_weight": false,
      "overrides": {
        "context_window_size": 2000,
        "prefill_chunk_size": 128
      }
    }
  ]
}