File size: 4,575 Bytes
e28cbc4
 
a29a6dc
 
e28cbc4
 
a29a6dc
 
e28cbc4
 
 
a29a6dc
e28cbc4
 
a29a6dc
e28cbc4
a29a6dc
 
e28cbc4
 
95a8c70
0f918ce
e28cbc4
 
a29a6dc
e28cbc4
 
a29a6dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e28cbc4
 
 
a29a6dc
e28cbc4
 
 
 
 
 
a29a6dc
e28cbc4
 
 
 
95a8c70
0f918ce
e28cbc4
 
 
 
 
a29a6dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e28cbc4
 
 
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
{
  "version": 1,
  "lifecycleSchemaVersion": 1,
  "updatedAt": "2026-03-05",
  "models": [
    {
      "modelId": "gemma-3-270m-it-wq4k-ef16-hf16",
      "preset": "gemma3",
      "label": "Gemma 3 270M Instruct (Q4K/F32a)",
      "description": "Gemma 3 270M text model. Prefers Hugging Face-hosted prebuilt RDRR shards with local curated fallback.",
      "modes": [
        "run"
      ],
      "aliases": [
        "gemma3-270m",
        "google/gemma-3-270m-it",
        "gemma-3-270m-it-wq4k-ef16",
        "gemma-3-270m-it-wq4k-ef16-hf16-f32"
      ],
      "hf": {
        "repoId": "Clocksmith/rdrr",
        "revision": "4efe64a914892e98be50842aeb16c3b648cc68a5",
        "path": "models/gemma-3-270m-it-wq4k-ef16"
      },
      "baseUrl": "./curated/gemma-3-270m-it-wq4k-ef16-hf16",
      "sizeBytes": 418512553,
      "recommended": false,
      "sortOrder": 10,
      "lifecycle": {
        "availability": {
          "curated": true,
          "local": true,
          "hf": true
        },
        "status": {
          "runtime": "active",
          "conversion": "ready",
          "demo": "curated",
          "tested": "verified"
        },
        "tested": {
          "suite": "inference",
          "surface": "auto",
          "result": "pass",
          "lastVerifiedAt": "2026-03-04",
          "source": "registry-verify"
        }
      }
    },
    {
      "modelId": "google-embeddinggemma-300m-wq4k-ef16",
      "preset": "embeddinggemma",
      "label": "EmbeddingGemma 300M (Q4K)",
      "description": "EmbeddingGemma sentence embedding model. Prefers Hugging Face-hosted prebuilt RDRR shards with local curated fallback.",
      "modes": [
        "embedding"
      ],
      "aliases": [
        "embeddinggemma-300m",
        "google/embeddinggemma-300m",
        "google-embeddinggemma-300m-wq4k-ef16"
      ],
      "hf": {
        "repoId": "Clocksmith/rdrr",
        "revision": "4efe64a914892e98be50842aeb16c3b648cc68a5",
        "path": "models/google-embeddinggemma-300m-wq4k-ef16"
      },
      "baseUrl": "./curated/google-embeddinggemma-300m-wq4k-ef16",
      "sizeBytes": 480562497,
      "recommended": false,
      "sortOrder": 11,
      "lifecycle": {
        "availability": {
          "curated": true,
          "local": true,
          "hf": true
        },
        "status": {
          "runtime": "active",
          "conversion": "ready",
          "demo": "curated",
          "tested": "verified"
        },
        "tested": {
          "suite": "inference",
          "surface": "auto",
          "result": "pass",
          "lastVerifiedAt": "2026-03-04",
          "source": "registry-verify"
        }
      }
    },
    {
      "modelId": "qwen-3-5-0-8b-wq4k-ef16-hf16-f16",
      "preset": "qwen3",
      "label": "Qwen 3.5 0.8B (Q4K)",
      "description": "Qwen 3.5 0.8B text model with hybrid linear attention. Q4K weights, F16 embeddings/head.",
      "modes": [
        "run"
      ],
      "aliases": [
        "qwen3-0.8b",
        "qwen-3-5-0-8b",
        "Qwen/Qwen3.5-0.8B"
      ],
      "hf": {
        "repoId": "Clocksmith/rdrr",
        "revision": null,
        "path": "models/qwen-3-5-0-8b-wq4k-ef16-hf16-f16"
      },
      "baseUrl": null,
      "sizeBytes": 788833984,
      "recommended": true,
      "sortOrder": 20,
      "lifecycle": {
        "availability": {
          "curated": false,
          "local": true,
          "hf": false
        },
        "status": {
          "runtime": "pending",
          "conversion": "ready",
          "demo": "none",
          "tested": "untested"
        },
        "tested": null
      }
    },
    {
      "modelId": "qwen-3-5-2b-wq4k-ef16-hf16-f16",
      "preset": "qwen3",
      "label": "Qwen 3.5 2B (Q4K)",
      "description": "Qwen 3.5 2B text model with hybrid linear attention. Q4K weights, F16 embeddings/head.",
      "modes": [
        "run"
      ],
      "aliases": [
        "qwen3-2b",
        "qwen-3-5-2b",
        "Qwen/Qwen3.5-2B"
      ],
      "hf": {
        "repoId": "Clocksmith/rdrr",
        "revision": null,
        "path": "models/qwen-3-5-2b-wq4k-ef16-hf16-f16"
      },
      "baseUrl": null,
      "sizeBytes": 1789738688,
      "recommended": true,
      "sortOrder": 21,
      "lifecycle": {
        "availability": {
          "curated": false,
          "local": true,
          "hf": false
        },
        "status": {
          "runtime": "pending",
          "conversion": "ready",
          "demo": "none",
          "tested": "untested"
        },
        "tested": null
      }
    }
  ]
}