Get the app
/ market / disenchantment

Disenchantment Index detail

The Disenchantment Index (DAI) measures, for each foundation model, what share of its download market has flowed into abliterated descendants at any tree depth. Named for Max Weber's Entzauberung - the disenchantment of the world - it quantifies how much of a base model's audience has chosen to strip away its safety guardrails. Full recursive fork tree; direct forks, forks-of-forks, and beyond.

8.26%
Market-wide weighted DAI
Up from 0.15% in 2024-10 - 53.6x over 24 months
478
Bases analyzed
All external foundation models with recorded downloads
316
Bases with 3+ descendants
Threshold for inclusion in the ranked table
316 of 316 shown
# Base model History Base downloads Descendants Descendant downloads DAI
1
lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled ACTIVE 46 forks
5,665 46 173,811 3068.2%
2
Qwen/Qwen-Image-2.1 ACTIVE 59 forks
94,556 59 1,809,624 1913.8%
3
ukisai/Swift-1.5-Qwen3.8-27b ACTIVE 9 forks
4,292 9 53,135 1238.0%
4
unsloth/Phi-3-mini-4k-instruct ACTIVE 8 forks
2,224 8 19,444 874.3%
5
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2 ACTIVE 16 forks
1,544 16 12,843 831.8%
6
empero-ai/Qwythos-9B-Claude-Mythos-5-1M INACTIVE 23 forks
8,019 23 62,883 784.2%
7
Accio-Lab/occamy-1.0 ACTIVE 3 forks
2,716 3 21,032 774.4%
8
empero-ai/Qwen3.8-35B-A3B-Distill ACTIVE 4 forks
6,757 4 51,740 765.7%
9
Jackrong/Qwopus3.6-27B-v2 INACTIVE 17 forks
1,298 17 7,552 581.8%
10
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2 INACTIVE 5 forks
1,018 5 5,678 557.8%
11
bottlecapai/ThinkingCap-Qwen3.8-27B ACTIVE 7 forks
1,180 7 5,503 466.4%
12
google/gemma-4-E4B-it-qat-q4_0-unquantized ACTIVE 7 forks
4,529 7 19,759 436.3%
13
google/gemma-4-12B-it-qat-q4_0-unquantized ACTIVE 20 forks
11,226 20 47,701 424.9%
14
NousResearch/Hermes-3-Llama-3.1-70B ACTIVE 8 forks
2,373 8 10,016 422.1%
15
ornith-ai/Ornith-1.5-9B ACTIVE 54 forks
450,460 54 1,829,451 406.1%
16
TheDrummer/Rocinante-X-12B-v1 ACTIVE 3 forks
1,393 3 5,443 390.7%
17
mkurman/Qwen2.5-14B-DeepSeek-R1-1M ACTIVE 8 forks
1,104 8 3,952 358.0%
18
GraySwanAI/Llama-3-8B-Instruct-RR ACTIVE 3 forks
1,453 3 4,464 307.2%
19
wangzhang/gemma-4-26B-A4B-it-abliterix ACTIVE 9 forks
1,100 9 3,358 305.3%
20
ukisai/Swift-Qwen3.8-27b ACTIVE 27 forks
22,311 27 62,543 280.3%
21
TenStrip/LTX2.3-10Eros ACTIVE 7 forks
47,374 7 127,700 269.6%
22
inflatebot/MN-12B-Mag-Mell-R1 ACTIVE 11 forks
2,528 11 6,756 267.3%
23
beomi/Llama-3-Open-Ko-8B ACTIVE 4 forks
2,490 4 6,391 256.7%
24
Qwen/Qwen-AgentWorld-35B-A3B INACTIVE 23 forks
8,274 23 16,354 197.7%
25
mistralai/Mistral-Small-Instruct-2409 ACTIVE 10 forks
6,115 10 12,025 196.7%
26
VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct ACTIVE 3 forks
1,723 3 3,386 196.5%
27
Qwen/Qwen3.8-27B ACTIVE 708 forks
6,758,884 708 13,272,511 196.4%
28
LiquidAI/LFM2-24B-A2B ACTIVE 8 forks
3,355 8 6,412 191.1%
29
nex-agi/Nex-N2.5-mini ACTIVE 7 forks
10,416 7 18,666 179.2%
30
Kwaipilot/KAT-Coder-V2.5-Dev ACTIVE 6 forks
10,342 6 17,061 165.0%
31
01-ai/Yi-1.5-9B-Chat-16K ACTIVE 4 forks
9,053 4 14,815 163.7%
32
ai9stars/G9v3-3B ACTIVE 4 forks
2,128 4 3,252 152.8%
33
InternScience/Agents-A1 INACTIVE 5 forks
5,686 5 8,604 151.3%
34
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B ACTIVE 5 forks
16,181 5 24,397 150.8%
35
hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled ACTIVE 11 forks
2,497 11 3,762 150.7%
36
reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B ACTIVE 3 forks
4,792 3 7,064 147.4%
37
nex-agi/Nex-N2-mini INACTIVE 10 forks
1,230 10 1,664 135.3%
38
Hcompany/Holo-3.1-9B INACTIVE 3 forks
1,453 3 1,822 125.4%
39
allenai/Llama-3.1-Tulu-3.1-8B ACTIVE 3 forks
1,304 3 1,586 121.6%
40
unsloth/gpt-oss-20b-BF16 ACTIVE 46 forks
84,106 46 99,282 118.0%
41
google/gemma-2-2b-jpn-it ACTIVE 18 forks
7,048 18 7,744 109.9%
42
NousResearch/Hermes-3-Llama-3.2-3B ACTIVE 4 forks
4,070 4 4,437 109.0%
43
nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct INACTIVE 4 forks
2,712 4 2,844 104.9%
44
inclusionAI/Ling-3.0-tiny ACTIVE 5 forks
16,312 5 16,707 102.4%
45
mistralai/Ministral-3-14B-Base-2512 INACTIVE 3 forks
3,706 3 3,667 99.0%
46
google/gemma-3n-E4B-it ACTIVE 26 forks
12,570 26 11,953 95.1%
47
sail/Sailor2-8B-Chat ACTIVE 4 forks
1,165 4 1,046 89.8%
48
internlm/internlm2_5-20b-chat ACTIVE 5 forks
1,431 5 1,283 89.7%
49
sbintuitions/sarashina2-7b ACTIVE 3 forks
1,415 3 1,233 87.1%
50
DeepHat/DeepHat-V1-7B ACTIVE 13 forks
4,424 13 3,844 86.9%
51
JetBrains/Mellum2-12B-A2.5B-Thinking ACTIVE 4 forks
2,094 4 1,817 86.8%
52
h2oai/h2o-danube2-1.8b-base ACTIVE 4 forks
3,451 4 2,915 84.5%
53
aisingapore/Qwen-SEA-LION-v4-4B-VL ACTIVE 3 forks
1,127 3 939 83.3%
54
Qwen/Qwen3.6-35B-A3B ACTIVE 312 forks
3,411,526 312 2,748,432 80.6%
55
Qwen/QwQ-32B-Preview ACTIVE 46 forks
11,580 46 8,877 76.7%
56
LiquidAI/LFM2.5-8B-A1B ACTIVE 29 forks
31,655 29 23,025 72.7%
57
01-ai/Yi-1.5-9B-Chat ACTIVE 5 forks
20,111 5 13,765 68.5%
58
AllThingsIntel/Apollo-V0.1-4B-Thinking ACTIVE 3 forks
1,682 3 1,144 68.0%
59
google/gemma-3-1b-it-qat-q4_0-unquantized ACTIVE 6 forks
1,192 6 798 67.0%
60
google/gemma-4-12B-it ACTIVE 146 forks
1,840,993 146 1,212,425 65.9%
61
WeiboAI/VibeThinker-1.5B ACTIVE 4 forks
9,053 4 5,796 64.0%
62
Qwen/Qwen3.6-27B INACTIVE 386 forks
2,384,695 386 1,446,814 60.7%
63
mistralai/Magistral-Small-2509 ACTIVE 8 forks
6,215 8 3,596 57.9%
64
krea/Krea-2-Turbo ACTIVE 3 forks
86,622 3 49,041 56.6%
65
deepseek-ai/DeepSeek-R1-Distill-Llama-70B INACTIVE 40 forks
65,592 40 36,359 55.4%
66
zai-org/GLM-4-32B-0414 ACTIVE 8 forks
5,475 8 2,967 54.2%
67
ornith-ai/Ornith-1.5-35B-A3B ACTIVE 54 forks
266,845 54 130,930 49.1%
68
Qwen/Qwen3-VL-30B-A3B-Thinking ACTIVE 11 forks
17,846 11 8,634 48.4%
69
Jackrong/Qwopus3.8-27B-Flash ACTIVE 6 forks
4,448 6 2,147 48.3%
70
ai-sage/GigaChat3.1-10B-A1.8B-bf16 ACTIVE 4 forks
5,722 4 2,732 47.8%
71
Qwen/Qwen3.5-122B-A10B ACTIVE 46 forks
555,162 46 264,444 47.6%
72
mistralai/Magistral-Small-2507 ACTIVE 3 forks
4,614 3 2,132 46.2%
73
Sao10K/L3-8B-Stheno-v3.2 ACTIVE 4 forks
10,093 4 4,498 44.6%
74
arcee-ai/Llama-3.1-SuperNova-Lite ACTIVE 3 forks
1,570 3 680 43.3%
75
Qwen/Qwen3-VL-32B-Thinking ACTIVE 11 forks
16,488 11 7,115 43.1%
76
Qwen/Qwen3.8-Flash-Next ACTIVE 76 forks
1,530,359 76 659,844 43.1%
77
mistralai/Ministral-3-8B-Base-2512 INACTIVE 8 forks
10,970 8 4,484 40.9%
78
WeiboAI/VibeThinker-3B ACTIVE 4 forks
4,787 4 1,939 40.5%
79
01-ai/Yi-1.5-34B-Chat ACTIVE 6 forks
15,546 6 6,166 39.7%
80
Nanbeige/Nanbeige4.1-3B ACTIVE 18 forks
5,032 18 1,961 39.0%
81
LiquidAI/LFM2.5-2.6B INACTIVE 20 forks
103,387 20 40,034 38.7%
82
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled ACTIVE 34 forks
21,771 34 7,669 35.2%
83
microsoft/Fara-7B ACTIVE 7 forks
9,860 7 3,418 34.7%
84
Hcompany/Holo-3.1-4B ACTIVE 6 forks
11,631 6 3,958 34.0%
85
Qwen/Qwen3-VL-32B-Instruct ACTIVE 28 forks
324,371 28 107,543 33.1%
86
Qwen/QwQ-32B ACTIVE 50 forks
48,911 50 15,852 32.4%
87
Qwen/Qwen3-30B-A3B-Thinking-2507 ACTIVE 37 forks
81,879 37 26,416 32.3%
88
black-forest-labs/FLUX.2-klein-9B ACTIVE 6 forks
198,349 6 62,435 31.5%
89
Qwen/Qwen3-Next-80B-A3B-Thinking ACTIVE 14 forks
41,140 14 12,598 30.6%
90
tencent/HY-MT1.5-1.8B ACTIVE 6 forks
6,609 6 2,004 30.3%
91
Qwen/Qwen2.5-32B ACTIVE 16 forks
29,266 16 8,473 28.9%
92
unsloth/Meta-Llama-3.1-70B-bnb-4bit ACTIVE 3 forks
3,851 3 1,071 27.8%
93
deepseek-ai/DeepSeek-V4.1-Flash ACTIVE 37 forks
869,321 37 235,877 27.1%
94
reaperdoesntknow/TopologicalQwen ACTIVE 3 forks
5,753 3 1,529 26.6%
95
google/gemma-2-27b-it ACTIVE 22 forks
21,148 22 5,530 26.1%
96
google/gemma-4-E2B-it-qat-q4_0-unquantized ACTIVE 3 forks
27,670 3 7,193 26.0%
97
LiquidAI/LFM2-8B-A1B ACTIVE 10 forks
18,831 10 4,876 25.9%
98
google/gemma-3-12b-it-qat-q4_0-unquantized ACTIVE 8 forks
11,946 8 2,967 24.8%
99
meta-llama/Llama-3.3-70B-Instruct ACTIVE 48 forks
389,444 48 85,616 22.0%
100
mistralai/Ministral-3-8B-Reasoning-2512 ACTIVE 4 forks
12,168 4 2,559 21.0%
101
unsloth/Llama-3.3-70B-Instruct-bnb-4bit INACTIVE 4 forks
12,724 4 2,413 19.0%
102
nvidia/Nemotron-Cascade-2-30B-A3B ACTIVE 3 forks
6,921 3 1,294 18.7%
103
unsloth/gemma-2-9b-it ACTIVE 3 forks
10,981 3 2,044 18.6%
104
arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled INACTIVE 3 forks
1,736 3 322 18.6%
105
CohereLabs/c4ai-command-a-03-2025 ACTIVE 3 forks
2,130 3 391 18.4%
106
arcee-ai/AFM-4.5B ACTIVE 3 forks
10,241 3 1,855 18.1%
107
inclusionAI/Ling-3.0-flash INACTIVE 3 forks
13,183 3 2,380 18.1%
108
meta-models/Muse-Glimmer-30B INACTIVE 45 forks
276,520 45 48,701 17.6%
109
deepseek-ai/DeepSeek-V4-Flash INACTIVE 16 forks
1,014,357 16 174,971 17.3%
110
Qwen/Qwen3-VL-4B-Thinking ACTIVE 13 forks
48,391 13 8,322 17.2%
111
TokenRhythm/NeoHorse-1-4B ACTIVE 4 forks
29,588 4 4,996 16.9%
112
unsloth/tinyllama-chat-bnb-4bit ACTIVE 5 forks
2,557 5 423 16.5%
113
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B ACTIVE 44 forks
430,537 44 67,794 15.8%
114
Qwen/Qwen3-Coder-30B-A3B-Instruct ACTIVE 11 forks
442,136 11 67,344 15.2%
115
Qwen/Qwen2.5-72B INACTIVE 9 forks
18,054 9 2,683 14.9%
116
LiquidAI/LFM2.5-1.2B-Thinking ACTIVE 3 forks
8,552 3 1,237 14.5%
117
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B ACTIVE 41 forks
266,719 41 36,155 13.6%
118
deepseek-ai/deepseek-llm-7b-chat ACTIVE 3 forks
22,340 3 2,922 13.1%
119
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF ACTIVE 3 forks
2,244,732 3 292,171 13.0%
120
mistralai/Mistral-Small-3.2-24B-Instruct-2506 ACTIVE 13 forks
256,615 13 33,390 13.0%
121
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B ACTIVE 56 forks
335,528 56 43,293 12.9%
122
black-forest-labs/FLUX.1-dev ACTIVE 69 forks
699,487 69 89,994 12.9%
123
mistralai/Mistral-Nemo-Instruct-2407 ACTIVE 36 forks
334,336 36 42,294 12.7%
124
prism-ml/Ternary-Bonsai-2-27B-mlx-2bit ACTIVE 4 forks
73,266 4 9,235 12.6%
125
Qwen/Qwen3-VL-30B-A3B-Instruct ACTIVE 15 forks
416,052 15 52,042 12.5%
126
Qwen/Qwen3.5-9B ACTIVE 194 forks
8,827,840 194 1,102,937 12.5%
127
google/gemma-4-26B-A4B-it-qat-q4_0-unquantized INACTIVE 19 forks
222,006 19 27,256 12.3%
128
Qwen/Qwen3.5-27B ACTIVE 105 forks
1,888,406 105 219,836 11.6%
129
Qwen/Qwen3.5-35B-A3B ACTIVE 154 forks
1,537,762 154 174,582 11.3%
130
google/gemma-4-31B-it INACTIVE 214 forks
9,872,605 214 1,112,358 11.3%
131
XHToken/Spark-X2.5-4B ACTIVE 4 forks
37,787 4 4,242 11.2%
132
deepseek-ai/DeepSeek-R1-Distill-Llama-8B ACTIVE 42 forks
190,050 42 20,898 11.0%
133
LiquidAI/LFM2-2.6B ACTIVE 5 forks
12,550 5 1,305 10.4%
134
google/gemma-3-12b-it ACTIVE 106 forks
452,772 106 45,474 10.0%
135
stepfun-ai/Step3-VL-10B ACTIVE 6 forks
27,150 6 2,701 9.9%
136
deepseek-ai/DeepSeek-V4-Flash-0731 INACTIVE 44 forks
4,536,688 44 450,081 9.9%
137
google/gemma-3-27b-it ACTIVE 79 forks
417,137 79 41,294 9.9%
138
Qwen/Qwen2.5-72B-Instruct ACTIVE 29 forks
283,941 29 27,535 9.7%
139
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF ACTIVE 5 forks
366,219 5 35,158 9.6%
140
Qwen/Qwen3-VL-8B-Thinking ACTIVE 18 forks
141,738 18 12,420 8.8%
141
prism-ml/Ternary-Bonsai-2-27B-gguf ACTIVE 14 forks
4,120,718 14 351,042 8.5%
142
BSC-LT/salamandra-7b-instruct ACTIVE 3 forks
26,516 3 2,220 8.4%
143
google/gemma-3-270m-it ACTIVE 16 forks
76,505 16 6,242 8.2%
144
google/gemma-4-26B-A4B-it ACTIVE 186 forks
12,724,590 186 1,002,339 7.9%
145
XiaomiMiMo/MiMo-V2.6-Flash-RL ACTIVE 7 forks
52,380 7 3,790 7.2%
146
google/gemma-4-26B-A4B ACTIVE 5 forks
47,553 5 3,383 7.1%
147
zai-org/GLM-5.3-Flash ACTIVE 56 forks
5,740,734 56 406,787 7.1%
148
Qwen/Qwen3-VL-8B-Instruct ACTIVE 56 forks
11,849,648 56 790,560 6.7%
149
LiquidAI/LFM2.5-1.2B-Instruct ACTIVE 29 forks
117,183 29 7,688 6.6%
150
mistralai/Ministral-3-14B-Reasoning-2512 ACTIVE 4 forks
71,679 4 4,642 6.5%
151
google/gemma-4-31B-it-qat-q4_0-unquantized INACTIVE 15 forks
288,845 15 18,479 6.4%
152
Hcompany/Holo-3.1-0.8B ACTIVE 3 forks
14,838 3 950 6.4%
153
Qwen/Qwen2.5-VL-7B-Instruct ACTIVE 23 forks
5,670,393 23 354,219 6.3%
154
Tongyi-MAI/Z-Image-Turbo ACTIVE 16 forks
587,729 16 36,706 6.3%
155
unsloth/llama-3-8b-bnb-4bit ACTIVE 5 forks
15,597 5 963 6.2%
156
Qwen/Qwen3-Coder-Next INACTIVE 17 forks
596,359 17 36,799 6.2%
157
Qwen/Qwen3-14B ACTIVE 56 forks
3,475,452 56 212,183 6.1%
158
ByteDance-Seed/Seed-OSS-36B-Instruct INACTIVE 4 forks
49,134 4 2,976 6.1%
159
unsloth/llama-3-8b-Instruct-bnb-4bit ACTIVE 3 forks
92,164 3 5,565 6.0%
160
google/gemma-2-9b ACTIVE 4 forks
34,971 4 2,045 5.8%
161
google/gemma-4-E4B-it ACTIVE 163 forks
4,438,133 163 245,824 5.5%
162
ibm-granite/granite-4.0-micro ACTIVE 6 forks
36,192 6 1,956 5.4%
163
google/gemma-3-4b-it ACTIVE 73 forks
1,237,067 73 65,577 5.3%
164
LiquidAI/LFM2.5-230M ACTIVE 8 forks
88,215 8 4,635 5.3%
165
poolside/Laguna-S-2.1 ACTIVE 12 forks
189,780 12 9,799 5.2%
166
XingChen-AGI/Xing4.0-29B-A4B ACTIVE 3 forks
50,497 3 2,575 5.1%
167
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp ACTIVE 12 forks
864,093 12 41,005 4.8%
168
MiniMaxAI/MiniMax-M3 INACTIVE 16 forks
185,785 16 8,735 4.7%
169
Qwen/Qwen3-30B-A3B INACTIVE 46 forks
1,446,040 46 62,557 4.3%
170
openbmb/MiniCPM-V-4.6 ACTIVE 18 forks
256,252 18 10,893 4.3%
171
internlm/internlm2_5-7b-chat ACTIVE 5 forks
34,774 5 1,471 4.2%
172
Qwen/Qwen3-30B-A3B-Instruct-2507 ACTIVE 18 forks
923,758 18 37,891 4.1%
173
mistralai/Mistral-Small-24B-Instruct-2501 ACTIVE 10 forks
59,469 10 2,350 4.0%
174
Qwen/Qwen3.5-9B-Base ACTIVE 29 forks
364,397 29 14,240 3.9%
175
ibm-granite/granite-3.3-2b-instruct ACTIVE 5 forks
49,279 5 1,831 3.7%
176
deepseek-ai/DeepSeek-V2-Lite-Chat ACTIVE 17 forks
140,638 17 5,160 3.7%
177
Qwen/Qwen3-VL-2B-Thinking ACTIVE 6 forks
111,659 6 4,056 3.6%
178
tencent/Hy-MT2-7B ACTIVE 3 forks
14,530 3 503 3.5%
179
zai-org/GLM-Z1-32B-0414 INACTIVE 4 forks
22,781 4 787 3.5%
180
Qwen/Qwen2.5-14B-Instruct-1M ACTIVE 4 forks
28,393 4 972 3.4%
181
google/gemma-4-E2B-it ACTIVE 109 forks
3,025,976 109 102,353 3.4%
182
Qwen/Qwen3-8B ACTIVE 101 forks
10,080,256 101 322,461 3.2%
183
Qwen/Qwen3-Next-80B-A3B-Instruct ACTIVE 29 forks
278,042 29 8,879 3.2%
184
Qwen/Qwen3-4B-Thinking-2507 ACTIVE 33 forks
558,712 33 17,674 3.2%
185
ibm-granite/granite-4.1-8b ACTIVE 8 forks
171,134 8 5,296 3.1%
186
mistralai/Mistral-Medium-3.5-128B ACTIVE 4 forks
102,582 4 3,155 3.1%
187
meta-llama/Llama-3.2-11B-Vision-Instruct ACTIVE 4 forks
69,648 4 2,060 3.0%
188
openbmb/MiniCPM-V-4.6-Thinking ACTIVE 4 forks
76,436 4 2,242 2.9%
189
unsloth/gemma-4-E4B-it INACTIVE 3 forks
54,584 3 1,573 2.9%
190
Qwen/Qwen2.5-7B ACTIVE 59 forks
803,080 59 22,695 2.8%
191
meta-llama/Llama-3.2-3B ACTIVE 11 forks
317,338 11 8,855 2.8%
192
Qwen/Qwen2.5-Coder-1.5B-Instruct ACTIVE 11 forks
491,277 11 13,583 2.8%
193
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF INACTIVE 7 forks
673,417 7 18,585 2.8%
194
mistralai/Ministral-3-14B-Instruct-2512 ACTIVE 7 forks
213,952 7 5,362 2.5%
195
HuggingFaceH4/zephyr-7b-beta ACTIVE 3 forks
86,714 3 2,064 2.4%
196
microsoft/Phi-4-mini-reasoning ACTIVE 4 forks
58,619 4 1,372 2.3%
197
LiquidAI/LFM2.5-350M ACTIVE 5 forks
64,902 5 1,512 2.3%
198
Qwen/Qwen2.5-14B INACTIVE 8 forks
81,425 8 1,878 2.3%
199
meta-llama/Llama-3.2-3B-Instruct ACTIVE 47 forks
1,628,863 47 37,635 2.3%
200
ibm-granite/granite-4.1-30b ACTIVE 10 forks
253,761 10 5,816 2.3%
201
meta-llama/Llama-4-Scout-17B-16E-Instruct INACTIVE 6 forks
172,694 6 3,455 2.0%
202
Qwen/Qwen3-VL-4B-Instruct ACTIVE 48 forks
3,407,511 48 67,461 2.0%
203
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B ACTIVE 30 forks
682,235 30 13,314 1.9%
204
TinyLlama/TinyLlama-1.1B-step-50K-105b ACTIVE 5 forks
32,845 5 638 1.9%
205
ibm-granite/granite-4.2-8b ACTIVE 5 forks
128,760 5 2,499 1.9%
206
SulphurAI/Sulphur-2-base ACTIVE 3 forks
175,335 3 3,378 1.9%
207
openbmb/MiniCPM-V-4_5 ACTIVE 3 forks
95,915 3 1,852 1.9%
208
mistralai/Devstral-Small-2-24B-Instruct-2512 ACTIVE 4 forks
316,487 4 6,071 1.9%
209
openbmb/MiniCPM5-1B ACTIVE 13 forks
408,311 13 7,826 1.9%
210
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B ACTIVE 32 forks
1,031,603 32 19,739 1.9%
211
HuggingFaceTB/SmolLM2-1.7B-Instruct ACTIVE 6 forks
190,951 6 3,584 1.9%
212
microsoft/Phi-4-mini-instruct ACTIVE 11 forks
363,242 11 6,582 1.8%
213
Qwen/Qwen3-235B-A22B ACTIVE 4 forks
474,847 4 8,527 1.8%
214
google/gemma-2-2b-it ACTIVE 14 forks
578,217 14 10,111 1.8%
215
zai-org/GLM-4.7-Flash ACTIVE 19 forks
1,677,746 19 28,321 1.7%
216
zai-org/GLM-5.1-FP8 ACTIVE 10 forks
26,649 10 430 1.6%
217
ibm-granite/granite-3.3-8b-instruct ACTIVE 5 forks
76,014 5 1,152 1.5%
218
microsoft/phi-4 ACTIVE 24 forks
426,836 24 6,235 1.5%
219
openbmb/MiniCPM5-2B ACTIVE 14 forks
1,145,692 14 16,702 1.5%
220
Qwen/Qwen2.5-VL-3B-Instruct ACTIVE 17 forks
2,292,740 17 32,896 1.4%
221
Qwen/Qwen2.5-32B-Instruct ACTIVE 32 forks
1,871,562 32 26,446 1.4%
222
zai-org/GLM-4.6V-Flash ACTIVE 6 forks
105,132 6 1,466 1.4%
223
Qwen/Qwen3.5-4B-Base ACTIVE 10 forks
630,171 10 8,504 1.4%
224
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 ACTIVE 11 forks
571,678 11 7,443 1.3%
225
google/gemma-2-9b-it ACTIVE 6 forks
1,026,916 6 12,794 1.3%
226
Qwen/Qwen3.5-4B ACTIVE 81 forks
7,968,478 81 98,540 1.2%
227
Qwen/Qwen2.5-Coder-7B-Instruct ACTIVE 19 forks
2,398,003 19 28,519 1.2%
228
Qwen/Qwen2.5-7B-Instruct ACTIVE 65 forks
8,272,384 65 97,524 1.2%
229
google/gemma-3-1b-it INACTIVE 38 forks
3,406,623 38 40,280 1.2%
230
Qwen/Qwen2.5-Coder-32B-Instruct INACTIVE 18 forks
863,297 18 10,047 1.2%
231
ibm-granite/granite-4.1-3b ACTIVE 16 forks
540,575 16 5,891 1.1%
232
Qwen/Qwen3.5-2B-Base ACTIVE 6 forks
286,285 6 3,093 1.1%
233
Qwen/Qwen3-4B-Instruct-2507 ACTIVE 60 forks
3,648,462 60 37,707 1.0%
234
Qwen/Qwen3.5-0.8B ACTIVE 50 forks
2,539,302 50 25,852 1.0%
235
Qwen/Qwen2.5-Coder-14B-Instruct ACTIVE 16 forks
1,622,509 16 15,858 1.0%
236
unsloth/Meta-Llama-3.1-8B-Instruct ACTIVE 8 forks
210,990 8 2,073 1.0%
237
Qwen/Qwen3.5-397B-A17B INACTIVE 6 forks
448,069 6 4,267 0.9%
238
google/gemma-4-E4B ACTIVE 5 forks
584,348 5 5,279 0.9%
239
Qwen/Qwen3-1.7B ACTIVE 51 forks
3,064,924 51 24,126 0.8%
240
zai-org/GLM-4.5V ACTIVE 4 forks
39,406 4 311 0.8%
241
mistralai/Mistral-7B-Instruct-v0.3 ACTIVE 12 forks
2,139,487 12 16,727 0.8%
242
Qwen/Qwen3.5-2B ACTIVE 40 forks
4,784,610 40 36,836 0.8%
243
Qwen/Qwen2.5-1.5B ACTIVE 13 forks
611,820 13 4,461 0.7%
244
google/diffusiongemma-26B-A4B-it INACTIVE 8 forks
576,872 8 4,212 0.7%
245
openai/gpt-oss-120b ACTIVE 28 forks
4,406,535 28 30,576 0.7%
246
stepfun-ai/Step-3.7-Flash INACTIVE 3 forks
24,744 3 168 0.7%
247
Qwen/Qwen2.5-14B-Instruct ACTIVE 39 forks
1,562,286 39 10,536 0.7%
248
Qwen/Qwen3-32B ACTIVE 30 forks
3,741,049 30 25,179 0.7%
249
Qwen/Qwen3.5-0.8B-Base ACTIVE 5 forks
425,099 5 2,864 0.7%
250
mistralai/Ministral-3-3B-Instruct-2512 ACTIVE 3 forks
113,410 3 735 0.7%
251
ornith-ai/Ornith-1.0-35B INACTIVE 12 forks
1,451,595 12 9,299 0.6%
252
nvidia/Cosmos-Reason2-8B INACTIVE 4 forks
164,207 4 980 0.6%
253
Qwen/Qwen2.5-3B-Instruct ACTIVE 39 forks
4,213,957 39 23,943 0.6%
254
meta-llama/Meta-Llama-3-8B-Instruct ACTIVE 26 forks
927,792 26 5,163 0.6%
255
zai-org/GLM-5.2 INACTIVE 17 forks
681,301 17 3,666 0.5%
256
Qwen/Qwen3-4B ACTIVE 60 forks
7,637,056 60 40,721 0.5%
257
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 INACTIVE 9 forks
353,994 9 1,793 0.5%
258
zai-org/GLM-5.3 ACTIVE 25 forks
1,436,511 25 7,020 0.5%
259
Qwen/Qwen3-VL-2B-Instruct ACTIVE 19 forks
2,773,921 19 13,463 0.5%
260
moonshotai/Kimi-K3 ACTIVE 12 forks
1,243,137 12 5,554 0.5%
261
allenai/Olmo-3-7B-Instruct ACTIVE 9 forks
476,182 9 2,143 0.5%
262
HuggingFaceTB/SmolLM3-3B ACTIVE 6 forks
628,733 6 2,858 0.5%
263
cross-encoder/nli-MiniLM2-L6-H768 ACTIVE 6 forks
257,754 6 1,129 0.4%
264
Qwen/Qwen3-Coder-480B-A35B-Instruct ACTIVE 3 forks
36,225 3 155 0.4%
265
OBLITERATUS/Qwen3.8-27B-OBLITERATED ACTIVE 4 forks
722,012 4 3,113 0.4%
266
google/medgemma-4b-it ACTIVE 10 forks
907,335 10 3,783 0.4%
267
Qwen/Qwen2-VL-2B-Instruct ACTIVE 6 forks
1,379,852 6 4,995 0.4%
268
MiniMaxAI/MiniMax-M2.5 ACTIVE 3 forks
495,509 3 1,613 0.3%
269
openai/gpt-oss-20b ACTIVE 29 forks
6,323,616 29 20,102 0.3%
270
Qwen/Qwen3-0.6B-Base ACTIVE 3 forks
728,089 3 2,287 0.3%
271
deepseek-ai/DeepSeek-V4-Flash-DSpark INACTIVE 8 forks
667,007 8 2,029 0.3%
272
MiniMaxAI/MiniMax-M2.7 ACTIVE 14 forks
1,018,598 14 2,780 0.3%
273
meta-llama/Llama-3.2-1B-Instruct ACTIVE 29 forks
7,494,880 29 19,540 0.3%
274
meta-llama/Llama-3.1-8B-Instruct ACTIVE 45 forks
6,104,298 45 15,589 0.3%
275
Qwen/Qwen3-4B-Base ACTIVE 6 forks
610,254 6 1,542 0.3%
276
Qwen/Qwen2.5-Coder-7B ACTIVE 9 forks
521,999 9 1,138 0.2%
277
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 INACTIVE 9 forks
2,753,879 9 5,365 0.2%
278
mistralai/Mistral-7B-Instruct-v0.2 ACTIVE 11 forks
1,660,754 11 3,010 0.2%
279
Qwen/Qwen3-0.6B ACTIVE 52 forks
30,037,022 52 53,948 0.2%
280
zai-org/GLM-4.5-Air ACTIVE 3 forks
454,649 3 763 0.2%
281
nvidia/Cosmos3-Nano ACTIVE 4 forks
96,937 4 168 0.2%
282
Qwen/Qwen2.5-Coder-3B-Instruct ACTIVE 3 forks
530,170 3 876 0.2%
283
Qwen/Qwen3-1.7B-Base ACTIVE 3 forks
656,551 3 994 0.1%
284
TinyLlama/TinyLlama-1.1B-Chat-v1.0 ACTIVE 8 forks
1,322,168 8 2,041 0.1%
285
Qwen/Qwen2.5-0.5B-Instruct ACTIVE 55 forks
8,635,884 55 13,384 0.1%
286
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 ACTIVE 4 forks
476,003 4 661 0.1%
287
EleutherAI/pythia-1b ACTIVE 3 forks
155,541 3 196 0.1%
288
codellama/CodeLlama-7b-Instruct-hf ACTIVE 3 forks
34,621 3 41 0.1%
289
Qwen/Qwen-Image ACTIVE 7 forks
256,491 7 266 0.1%
290
Qwen/Qwen3.8-Flash-Next-FP8 ACTIVE 3 forks
385,353 3 337 0.1%
291
meta-llama/Llama-3.1-8B ACTIVE 10 forks
632,999 10 597 0.1%
292
Qwen/Qwen2.5-VL-32B-Instruct ACTIVE 3 forks
792,676 3 627 0.1%
293
meta-llama/Llama-2-7b-chat-hf ACTIVE 3 forks
426,308 3 312 0.1%
294
tencent/Hy3 INACTIVE 3 forks
372,392 3 269 0.1%
295
moonshotai/Kimi-K2.5 ACTIVE 6 forks
326,693 6 185 0.1%
296
zai-org/GLM-5 ACTIVE 6 forks
447,689 6 283 0.1%
297
unsloth/Qwen2.5-3B-Instruct ACTIVE 3 forks
23,145 3 10 0.0%
298
Qwen/Qwen2-VL-7B-Instruct ACTIVE 4 forks
610,590 4 188 0.0%
299
Qwen/Qwen3.8-27B-FP8 ACTIVE 4 forks
4,801,627 4 1,509 0.0%
300
meta-llama/Llama-3.2-1B ACTIVE 3 forks
723,128 3 194 0.0%
301
Qwen/Qwen2.5-1.5B-Instruct ACTIVE 11 forks
7,122,423 11 2,311 0.0%
302
FacebookAI/roberta-base ACTIVE 6 forks
8,004,938 6 1,282 0.0%
303
zai-org/GLM-5.1 ACTIVE 5 forks
316,149 5 75 0.0%
304
mistralai/Mistral-7B-v0.1 ACTIVE 4 forks
410,295 4 77 0.0%
305
deepseek-ai/DeepSeek-V3 ACTIVE 6 forks
1,370,380 6 142 0.0%
306
distilbert/distilbert-base-uncased ACTIVE 4 forks
8,226,537 4 624 0.0%
307
Qwen/Qwen3-8B-Base ACTIVE 6 forks
749,410 6 42 0.0%
308
allenai/Olmo-3-7B-Think ACTIVE 3 forks
452,109 3 38 0.0%
309
google/electra-base-discriminator ACTIVE 7 forks
45,905,787 7 1,188 0.0%
310
google-bert/bert-base-uncased ACTIVE 7 forks
38,734,727 7 1,276 0.0%
311
Qwen/Qwen3-Embedding-0.6B ACTIVE 6 forks
9,347,160 6 11 0.0%
312
unsloth/Llama-3.2-1B ACTIVE 3 forks
131,074 3 0 0.0%
313
google/gemma-3-1b-pt ACTIVE 4 forks
56,158 4 0 0.0%
314
unsloth/gpt-oss-120b-unsloth-bnb-4bit ACTIVE 3 forks
4,289 3 0 0.0%
315
moonshotai/Kimi-K2.6 ACTIVE 5 forks
463,718 5 0 0.0%
316
Wan-AI/Wan2.2-I2V-A14B ACTIVE 4 forks
11,434 4 0 0.0%
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration