dgx-spark-inference-stack/opencode.json at main · jdaln/dgx-spark-inference-stack · 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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
{
  "$schema": "https://opencode.ai/config.json",
  "permission": {
    "bash": "allow",
    "read": "allow",
    "edit": "allow",
    "grep": "allow",
    "glob": "allow",
    "list": "allow"
  },
  "enabled_providers": [
    "dgx"
  ],
  "provider": {
    "dgx": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "DGX Spark (local)",
      "options": {
        "baseURL": "http://localhost:8009/v1",
        "apiKey": "63TestTOKEN0REPLACEME"
      },
      "models": {
        "gpt-oss-20b": {
          "name": "GPT-OSS 20B",
          "limit": {
            "context": 131072,
            "output": 8192
          }
        },
        "gpt-oss-120b": {
          "name": "GPT-OSS 120B",
          "limit": {
            "context": 131072,
            "output": 8192
          }
        },
        "gemma4-26b-a4b": {
          "name": "Gemma 4 26B A4B",
          "reasoning": true,
          "tool_call": true,
          "limit": {
            "context": 262144,
            "output": 8192
          },
          "options": {
            "temperature": 1,
            "top_p": 0.95,
            "top_k": 64
          }
        },
        "qwen3.8-flash-next-nvfp4": {
          "name": "Qwen 3.8 Flash Next NVFP4",
          "reasoning": true,
          "tool_call": true,
          "limit": {
            "context": 262144,
            "output": 8192
          }
        },
        "qwen3.8-27b-nvfp4-dflash2": {
          "name": "Qwen 3.8 27B NVFP4 DFlash2",
          "reasoning": true,
          "tool_call": true,
          "limit": {
            "context": 262144,
            "output": 8192
          }
        },
        "lfm2.5-1.2b": {
          "name": "LFM2.5 1.2B Instruct",
          "reasoning": false,
          "tool_call": false,
          "limit": {
            "context": 32768,
            "output": 4096
          }
        },
        "huihui-gpt-oss-120b-mxfp4-abliterated": {
          "name": "Huihui GPT-OSS 120B Abliterated (MXFP4)",
          "reasoning": true,
          "limit": {
            "context": 131072,
            "output": 8192
          }
        },
        "huihui-qwen3.8-27b-abliterated-nvfp4": {
          "name": "Huihui Qwen3.8 27B Abliterated (NVFP4)",
          "reasoning": true,
          "tool_call": true,
          "limit": {
            "context": 262144,
            "output": 8192
          }
        }
      }
    }
  },
  "model": "dgx/qwen3.8-27b-nvfp4-dflash2",
  "small_model": "dgx/lfm2.5-1.2b",
  "compaction": {
    "auto": false
  },
  "logLevel": "ERROR"
}