-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcatalog.json
More file actions
188 lines (188 loc) · 7.43 KB
/
catalog.json
File metadata and controls
188 lines (188 loc) · 7.43 KB
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
[
{
"id": "qwen3_0_6b",
"display_name": "Qwen 3 0.6B",
"description": "Alibaba's latest tiny model with native thinking capability. Best quality at this size.",
"size_bytes": 490000000,
"size_label": "~0.46 GB",
"download_url": "https://huggingface.co/unsloth/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q4_K_M.gguf",
"file_name": "qwen3_0_6b_q4.gguf",
"min_ram_gb": 2,
"provider": "ALIBABA",
"context_length": 4096,
"supports_thinking": true
},
{
"id": "gemma3_1b",
"display_name": "Gemma 3 1B",
"description": "Google's 1B model with best-in-class accuracy at this size and strong instruction following.",
"size_bytes": 752000000,
"size_label": "~0.70 GB",
"download_url": "https://huggingface.co/lmstudio-community/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it-Q4_K_M.gguf",
"file_name": "gemma3_1b_q4.gguf",
"min_ram_gb": 2,
"provider": "GOOGLE",
"context_length": 8192,
"supports_thinking": false
},
{
"id": "qwen3_1_7b",
"display_name": "Qwen 3 1.7B",
"description": "Alibaba's 1.7B thinking model. Punches above its weight on reasoning tasks.",
"size_bytes": 1170000000,
"size_label": "~1.09 GB",
"download_url": "https://huggingface.co/unsloth/Qwen3-1.7B-GGUF/resolve/main/Qwen3-1.7B-Q4_K_M.gguf",
"file_name": "qwen3_1_7b_q4.gguf",
"min_ram_gb": 3,
"provider": "ALIBABA",
"context_length": 8192,
"supports_thinking": true
},
{
"id": "deepseek_r1_distill_1_5b",
"display_name": "DeepSeek-R1 1.5B",
"description": "DeepSeek's smallest reasoning model. Full chain-of-thought at just 1.1 GB.",
"size_bytes": 1203000000,
"size_label": "~1.12 GB",
"download_url": "https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf",
"file_name": "deepseek_r1_distill_1_5b_q4.gguf",
"min_ram_gb": 3,
"provider": "DEEPSEEK",
"context_length": 32768,
"supports_thinking": true
},
{
"id": "smollm3_3b",
"display_name": "SmolLM3 3B",
"description": "HuggingFace's mobile-first 3B model. Outperforms Llama 3.2 3B on benchmarks, great for on-device use.",
"size_bytes": 2062925824,
"size_label": "~1.92 GB",
"download_url": "https://huggingface.co/ggml-org/SmolLM3-3B-GGUF/resolve/main/SmolLM3-Q4_K_M.gguf",
"file_name": "smollm3_3b_q4.gguf",
"min_ram_gb": 3,
"provider": "HUGGINGFACE",
"context_length": 8192,
"supports_thinking": false
},
{
"id": "gemma3_4b",
"display_name": "Gemma 3 4B",
"description": "Google's 4B model with strong multimodal reasoning and instruction following.",
"size_bytes": 2670000000,
"size_label": "~2.49 GB",
"download_url": "https://huggingface.co/lmstudio-community/gemma-3-4b-it-GGUF/resolve/main/gemma-3-4b-it-Q4_K_M.gguf",
"file_name": "gemma3_4b_q4.gguf",
"min_ram_gb": 4,
"provider": "GOOGLE",
"context_length": 8192,
"supports_thinking": false
},
{
"id": "phi4_mini",
"display_name": "Phi-4 Mini",
"description": "Microsoft's latest compact model. State-of-the-art reasoning and coding at under 4B parameters.",
"size_bytes": 2673666867,
"size_label": "~2.49 GB",
"download_url": "https://huggingface.co/lmstudio-community/Phi-4-mini-instruct-GGUF/resolve/main/Phi-4-mini-instruct-Q4_K_M.gguf",
"file_name": "phi4_mini_q4.gguf",
"min_ram_gb": 4,
"provider": "MICROSOFT",
"context_length": 16384,
"supports_thinking": false
},
{
"id": "qwen3_5_4b",
"display_name": "Qwen 3.5 4B",
"description": "Alibaba's latest 4B with 262K context and native thinking. Best thinking model in this RAM tier.",
"size_bytes": 2944000000,
"size_label": "~2.74 GB",
"download_url": "https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/Qwen3.5-4B-Q4_K_M.gguf",
"file_name": "qwen3_5_4b_q4.gguf",
"min_ram_gb": 4,
"provider": "ALIBABA",
"context_length": 32768,
"supports_thinking": true
},
{
"id": "gemma4_e2b",
"display_name": "Gemma 4 E2B",
"description": "Google's on-device flagship from the Gemma 4 family. 5.1B total / 2.3B effective params, 128K context, built from Gemini 3 research.",
"size_bytes": 3339506483,
"size_label": "~3.11 GB",
"download_url": "https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF/resolve/main/gemma-4-E2B-it-Q4_K_M.gguf",
"file_name": "gemma4_e2b_q4.gguf",
"min_ram_gb": 5,
"provider": "GOOGLE",
"context_length": 131072,
"supports_thinking": false,
"is_available": false,
"unavailable_reason": "Awaiting runtime support for the Gemma 4 architecture in the bundled inference engine."
},
{
"id": "deepseek_r1_distill_7b",
"display_name": "DeepSeek-R1 7B",
"description": "DeepSeek's distilled 7B reasoning model. Outperforms larger models on math and logic benchmarks.",
"size_bytes": 5030000000,
"size_label": "~4.68 GB",
"download_url": "https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GGUF-Q4_K_M.gguf",
"file_name": "deepseek_r1_distill_7b_q4.gguf",
"min_ram_gb": 8,
"provider": "DEEPSEEK",
"context_length": 32768,
"supports_thinking": true
},
{
"id": "gemma4_e4b",
"display_name": "Gemma 4 E4B",
"description": "Google's larger on-device Gemma 4 model. 4B effective params, 128K context, strong multilingual and agentic reasoning for high-end phones.",
"size_bytes": 5347737600,
"size_label": "~4.98 GB",
"download_url": "https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_K_M.gguf",
"file_name": "gemma4_e4b_q4.gguf",
"min_ram_gb": 8,
"provider": "GOOGLE",
"context_length": 131072,
"supports_thinking": false,
"is_available": false,
"unavailable_reason": "Awaiting runtime support for the Gemma 4 architecture in the bundled inference engine."
},
{
"id": "qwen3_5_9b",
"display_name": "Qwen 3.5 9B",
"description": "Alibaba's top 9B with 262K context and thinking mode. The most downloaded GGUF of 2026.",
"size_bytes": 6100000000,
"size_label": "~5.68 GB",
"download_url": "https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q4_K_M.gguf",
"file_name": "qwen3_5_9b_q4.gguf",
"min_ram_gb": 8,
"provider": "ALIBABA",
"context_length": 32768,
"supports_thinking": true
},
{
"id": "qwen2_5_14b",
"display_name": "Qwen 2.5 14B",
"description": "Alibaba's capable 14B model. Best non-thinking option for high-end devices \u2014 strong coding, math, and multilingual.",
"size_bytes": 9655000000,
"size_label": "~8.99 GB",
"download_url": "https://huggingface.co/bartowski/Qwen2.5-14B-Instruct-GGUF/resolve/main/Qwen2.5-14B-Instruct-Q4_K_M.gguf",
"file_name": "qwen2_5_14b_q4.gguf",
"min_ram_gb": 14,
"provider": "ALIBABA",
"context_length": 32768,
"supports_thinking": false
},
{
"id": "deepseek_r1_distill_14b",
"display_name": "DeepSeek-R1 14B",
"description": "DeepSeek's distilled 14B reasoning model. Surpasses OpenAI o1-mini on AIME and MATH-500 benchmarks.",
"size_bytes": 9655000000,
"size_label": "~8.99 GB",
"download_url": "https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf",
"file_name": "deepseek_r1_distill_14b_q4.gguf",
"min_ram_gb": 16,
"provider": "DEEPSEEK",
"context_length": 32768,
"supports_thinking": true
}
]