fastgpu commited on
Commit
4dd75d5
·
verified ·
1 Parent(s): 97872e0

Model list 2026-10-31: 157 models added to search (12,716), 16 new among the 200 trending models on the card

Browse files
Files changed (4) hide show
  1. README.md +124 -124
  2. catalog-more.js +0 -0
  3. catalog.js +0 -0
  4. catalog.meta.json +1 -1
README.md CHANGED
@@ -21,204 +21,204 @@ datasets:
21
  models:
22
  - deepseek-ai/DeepSeek-V4.1-Flash-1017
23
  - Nanbeige/Nanbeige4.3-33B
 
 
24
  - RecursiveSI/flint
25
  - XHToken/Spark-X2.6-4B
26
- - ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
27
- - baidu/Unlimited-OCR-2
28
- - MiniMaxAI/MiniMax-M3.1-Flash
29
  - nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
30
- - HuggingFaceBio/Carbon-X
31
  - Diffuspace/Clover-35B-A3B-Preview
 
32
  - fishaudio/drama-3
33
- - unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF
34
  - XHToken/Spark-X2.6-4B-GGUF
35
- - unsloth/flint-GGUF
36
- - Qwen/Qwen3.8-Flash-Next
37
  - ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
38
- - Pika-Labs/Pika-H3-Flex
39
- - InternScience/Sage-A1.5
40
- - ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
41
  - BreezeBlue/Breeze-TTS-2
 
 
 
 
 
42
  - black-forest-labs/flux-3-image-klein
 
43
  - jialinyyzz/humanizer
44
- - OpenMOSS-Team/MOSS-Image-Base
45
- - divagr1925/Qwen3.5-4B-Qwenputer
46
- - inclusionAI/Ling-3.1-flash-1019
47
- - tencent/WeVisOne-VL-4B
48
- - KRAFTON/Raon-1-mini-preview
49
- - MemTensor/MemT-1.0-Nano
50
  - Nanbeige/Nanbeige4.3-33B-Base
51
  - deepseek-ai/DeepSeek-V4.1-Flash
52
- - briaai/Fibo-2.0-dev
 
 
 
 
 
53
  - ConwayResearch/Underdog-Saluki-27B-1.0
54
  - moonshotai/Kimi-K3
55
  - ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
56
- - gugujiji/novel-humanize-4b
57
- - nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
58
- - lodestones/Kromoss
59
- - prism-ml/Ternary-Bonsai-2-27B-gguf
60
  - zai-org/GLM-5.3-Flash
61
- - sensenova/SenseNova-6.8-Code2Video
62
- - ornith-ai/Ornith-1.5-122B
63
  - AtomicChat/Nanbeige4.3-33B-GGUF
64
- - Cloudflare/clef
65
  - kaitchup/Qwen3.8-27B-SLQ-GGUF
66
- - reflection/Beam-1.0-501B-A23B
 
 
 
67
  - GrootTeam/Groot-19B-A3B-261023
68
- - agentionai/Qwen3.8-Flash-Next-Gyro-GGUF
69
  - peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
70
  - Octen/Octen-WebGR-4B
71
- - inclusionAI/Ling-3.0-flash-Sante
 
 
 
72
  - nvidia/Qwen3.8-Flash-Next-FP4-Local
 
 
 
 
73
  - baidu/Unlimited-OCR
74
  - Qwen/Qwen-Image-2.1-Turbo
75
- - krea/Krea-2-Raw
 
 
76
  - meta-models/Muse-Spark-Open-816B-A42B
 
 
 
77
  - unsloth/MiniMax-M3.1-Flash-GGUF
78
- - GroundingPI/GroundAnything-VLM
79
- - zai-org/GLM-5.3
80
- - ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
81
  - briaai/Fibo-2.0-edit-turbo
82
- - abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF
83
- - nvidia/Qwen3.8-Flash-Next-NVFP4
84
- - fastino/GLiDE
85
  - unsloth/Qwen3.8-Flash-Next-GGUF
86
- - unsloth/DeepSeek-V4.1-Flash-1017-GGUF
87
- - MemTensor/MemT-1.0-Flash
88
- - agentionai/Qwen3.8-Flash-Next-Gyro-Coder-GGUF
89
- - DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
90
  - XingChen-AGI/Xing4.0-29B-Intent
91
- - Apexintelligence-AI/Apex-35B-V1.0
92
  - empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF
93
- - black-forest-labs/flux-3-image-klein-base
94
- - tencent/Hy-Memory-30B-A3B
95
  - ornith-ai/Ornith-1.5-9B-GGUF
96
- - KRAFTON/Raon-1-mini-preview-gguf
 
 
97
  - BAAI/AREX-2
 
 
 
98
  - yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
 
 
99
  - meta-models/Muse-Glimmer-30B
100
- - Qwen/Qwen3.6-35B-A3B
101
- - unsloth/Qwen3.6-35B-A3B-GGUF
102
  - nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
103
- - nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
104
- - HemmingwayAI/Hemmingway-1.5
105
- - google/gemma-4-E4B-it
106
  - InternScience/Sage-A1.5-Q4_K_M-GGUF
107
- - Aleph-Alpha/Kolibri-1
108
- - bottlecapai/ThinkingCap-gemma-4-26B-A4B-it
109
- - black-forest-labs/FLUX.2-dev
110
- - lodestones/Chroma1-HD
111
- - LiquidAI/LFM2.5-24B-A2B
112
- - Cloudflare/clef-flash
113
- - google/medgemma-1.5-4b-it
114
- - XiaomiMiMo/MiMo-V2.6-Pro-RL
115
- - bartowski/Nanbeige_Nanbeige4.3-33B-GGUF
116
- - nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16
117
  - unsloth/Qwen-Image-2.1-GGUF
118
- - LiquidAI/d1-3B
 
 
 
119
  - webbrain-one/Nanbeige4.3-33B-NVFP4
120
  - destined/hurston-1
121
  - unsloth/Ornith-1.5-122B-GGUF
122
  - GrootTeam/Groot-19B-A3B-261023-GGUF
123
  - Aratako/Drama-3-Japanese
124
- - peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF
125
- - peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
126
- - RecursiveSI/flint-nvfp4-gguf
127
- - datalab-to/chandra-ocr-2
128
- - deepseek-ai/DeepSeek-V4-Flash
129
- - bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
130
- - meta-models/Muse-Spark-Open-816B-A42B-NVFP4
131
  - ukisai/Swift-1.5-Qwen3.8-27B-GGUF
132
- - ukisai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-GGUF
 
 
 
 
 
 
133
  - JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF
134
- - unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
 
135
  - google/gemma-4-26B-A4B-it
 
 
 
 
 
136
  - inclusionAI/Ming-3.0-tts-tiny
137
- - ornith-ai/Ornith-1.5-35B-A3B-GGUF
138
- - prism-ml/Ternary-Bonsai-2-9B-gguf
139
  - Qwen/Qwen3-8B-GGUF
140
- - ornith-ai/Ornith-1.5-35B-A3B
141
- - XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
142
  - unsloth/Qwen3.5-9B-GGUF
143
  - fishaudio/s2-pro
144
- - peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF
145
- - unsloth/Qwen3.5-4B-GGUF
146
- - peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF
147
- - google/gemma-4-12B-it-qat-q4_0-gguf
148
  - Qwen/Qwen2.5-Coder-7B-Instruct-GGUF
149
- - Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata
150
  - stabilityai/stable-diffusion-3.5-medium
151
  - RavichandranJ/Dolphin3-Cyber-8B-GGUF
152
- - akhaliq/MOSS-Image-SFT-4-steps
153
- - Nanbeige/Nanbeige4.2-3B
154
  - google/gemma-4-12B-it
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
  - ibm-granite/granite-switch-4.1-8b
 
 
156
  - kaushikvira/DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata
157
- - google/gemma-4-E2B-it
 
 
 
 
 
158
  - RecursiveSI/flint-int4-gguf
159
- - Qwen/Qwen3.8-2.4T-A95B
160
- - XHToken/Spark-X2.6-4B-Base
161
- - inclusionAI/Ling-3.1-flash-base
162
  - LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF
163
- - ibm-granite/granite-switch-4.1-30b
164
- - basecompute/Qwen3.8-27B-BaseQuant-V1
165
- - unsloth/GLM-5.3-Flash-GGUF
166
  - Qwen/Qwen3-4B-Instruct-2507
167
- - empero-ai/Qwythos-9B-Claude-Mythos-5-1M
168
- - IsValorum/Flint-APEX-I-MiniPlus-V2.1-GGUF
169
- - ornith-ai/Ornith-1.5-9B
170
  - ornith-ai/Ornith-1.5-122B-GGUF
171
  - meta-llama/Llama-3.2-3B
172
- - Lightricks/LTX-2.5-Diffusers
173
- - abacusai/Smaug-Humanizer
 
 
 
 
 
 
 
 
 
 
 
 
 
 
174
  - microsoft/Sentiment-Analysis-7B
175
- - Teriminal-RSI/Terminal-RSI-27B
176
- - unsloth/LFM2.5-24B-A2B-GGUF
177
  - unsloth/MOSS-Image-SFT-GGUF
178
- - nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
179
- - incoai/Qwen3.8-27B-DFlash2
180
- - Diffuspace/Clover-35B-A3B-Preview-GGUF
181
  - HuggingFaceBio/Carbon-X-GGUF
182
- - nvidia/Qwen3.8-27B-NVFP4
183
  - google/gemma-4-E4B
184
- - DogukanUrker/Nanbeige4.3-33B-GGUF
185
  - NousResearch/Hermes-3-Llama-3.1-8B
186
- - ProCreations/Nanbeige4.3-33B-DFlash2
187
- - stabilityai/stable-diffusion-3.5-large
188
- - zai-org/GLM-5.2
189
- - kaitchup/Qwen3.8-27B-SLQ-EAR98
190
- - deepseek-ai/DeepSeek-V4-Pro
191
  - abenzerps/Nemotron-3.5-Bolt-E4B-GSQ-RCO-GGUF
192
- - diffbot/DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000
193
- - higa2515/gemma-4-12B-gay
194
  - ornith-ai/Ornith-1.5-122B-NVFP4
195
- - unsloth/GLM-4.7-Flash-GGUF
196
- - unsloth/Qwen-Image-2.1-Turbo-GGUF
197
- - google/gemma-4-12B
198
  - LiquidAI/LFM2.5-24B-A2B-GGUF
199
- - poolside/Laguna-S-2.1
200
- - axiomofmind/Moss-Image-SFT-GGUF
201
  - abenzerps/Spark-X2.6-4B-Quantized
202
- - bartowski/HemmingwayAI_Hemmingway-1.5-GGUF
203
  - bartowski/Spark-X2.6-4B-GGUF
204
- - ceia-br/lumi-4b
205
- - empero-ai/Qwen3.8-9B-Distill-GGUF
206
  - inclusionAI/Ling-3.0-tiny
207
- - jialinyyzz/humanizer-GGUF
208
- - microsoft/Phi-4-mini-instruct
209
- - Qwen/Qwen3-Coder-Next
210
- - sabicap/sabi-noema
211
  - SuperLogic/Qwen3.8-27B-Flash-MTP-GGUF
 
 
 
 
 
 
 
 
 
 
212
  - Wan-AI/Wan2.1-T2V-14B
213
  - YoSaNoo/Forge-1-Gemma-4-E2B
214
- - yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
215
- - deepseek-ai/DeepSeek-V4-Flash-0731
216
- - google/gemma-4-E2B
217
- - IFM/K2-Horizon-7B
218
- - IFM/K2-Horizon-MoVA-36B-A4B
219
  - inclusionAI/Ling-3.1-flash
220
- - meta-llama/Llama-2-7b-hf
221
- - nvidia/NLD-Uni
222
  ---
223
 
224
  # VRAM & GPU Cost Calculator
@@ -232,7 +232,7 @@ It reads each model's own metadata from the Hub (the parameter count in its safe
232
 
233
  ## Which models
234
 
235
- Any public model on the Hub that publishes a parameter count. The search box lists 12,559 of them: the text, vision-language, image, video, speech and embedding models the Hub counted at 1,000 or more downloads in the 30 days before a build day from 2026-10-11 to 2026-10-30, plus the ones trending on those days. Left out of the list: models too small to need a rented GPU, adult and refusal-stripped fine-tunes, and builds for Apple silicon, CPUs or phones. Anything else is found through the Hub's own search as you type, or by pasting its `org/name`.
236
 
237
  ## How the memory is sized
238
 
 
21
  models:
22
  - deepseek-ai/DeepSeek-V4.1-Flash-1017
23
  - Nanbeige/Nanbeige4.3-33B
24
+ - baidu/Unlimited-OCR-2
25
+ - ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
26
  - RecursiveSI/flint
27
  - XHToken/Spark-X2.6-4B
28
+ - Pika-Labs/Pika-H3-Flex
 
 
29
  - nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB
30
+ - MiniMaxAI/MiniMax-M3.1-Flash
31
  - Diffuspace/Clover-35B-A3B-Preview
32
+ - HuggingFaceBio/Carbon-X
33
  - fishaudio/drama-3
 
34
  - XHToken/Spark-X2.6-4B-GGUF
 
 
35
  - ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
36
+ - Qwen/Qwen3.8-Flash-Next
37
+ - unsloth/flint-GGUF
38
+ - divagr1925/Qwen3.5-4B-Qwenputer
39
  - BreezeBlue/Breeze-TTS-2
40
+ - unsloth/DeepSeek-V4.1-Flash-1017-GGUF
41
+ - ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
42
+ - unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF
43
+ - InternScience/Sage-A1.5
44
+ - inclusionAI/Ling-3.1-flash-1019
45
  - black-forest-labs/flux-3-image-klein
46
+ - sensenova/SenseNova-Loop-9B-Preview
47
  - jialinyyzz/humanizer
 
 
 
 
 
 
48
  - Nanbeige/Nanbeige4.3-33B-Base
49
  - deepseek-ai/DeepSeek-V4.1-Flash
50
+ - tencent/WeVisOne-VL-4B
51
+ - MemTensor/MemT-1.0-Nano
52
+ - OpenMOSS-Team/MOSS-Image-Base
53
+ - KRAFTON/Raon-1-mini-preview
54
+ - sensenova/SenseNova-6.8-Code2Video
55
+ - gugujiji/novel-humanize-4b
56
  - ConwayResearch/Underdog-Saluki-27B-1.0
57
  - moonshotai/Kimi-K3
58
  - ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
 
 
 
 
59
  - zai-org/GLM-5.3-Flash
 
 
60
  - AtomicChat/Nanbeige4.3-33B-GGUF
 
61
  - kaitchup/Qwen3.8-27B-SLQ-GGUF
62
+ - briaai/Fibo-2.0-dev
63
+ - Cloudflare/clef
64
+ - lodestones/Kromoss
65
+ - prism-ml/Ternary-Bonsai-2-27B-gguf
66
  - GrootTeam/Groot-19B-A3B-261023
 
67
  - peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
68
  - Octen/Octen-WebGR-4B
69
+ - ornith-ai/Ornith-1.5-122B
70
+ - agentionai/Qwen3.8-Flash-Next-Gyro-GGUF
71
+ - GroundingPI/GroundAnything-VLM
72
+ - reflection/Beam-1.0-501B-A23B
73
  - nvidia/Qwen3.8-Flash-Next-FP4-Local
74
+ - abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF
75
+ - nvidia/DeepSeek-V4.1-Flash-1017-NVFP4
76
+ - krea/Krea-2-Raw
77
+ - ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF
78
  - baidu/Unlimited-OCR
79
  - Qwen/Qwen-Image-2.1-Turbo
80
+ - zai-org/GLM-5.3
81
+ - nvidia/Qwen3.8-Flash-Next-NVFP4
82
+ - microsoft/Mage-VL-Cowork
83
  - meta-models/Muse-Spark-Open-816B-A42B
84
+ - MemTensor/MemT-1.0-Flash
85
+ - Apexintelligence-AI/Apex-35B-V1.0
86
+ - inclusionAI/Ling-3.0-flash-Sante
87
  - unsloth/MiniMax-M3.1-Flash-GGUF
 
 
 
88
  - briaai/Fibo-2.0-edit-turbo
 
 
 
89
  - unsloth/Qwen3.8-Flash-Next-GGUF
90
+ - HemmingwayAI/Hemmingway-1.5
 
 
 
91
  - XingChen-AGI/Xing4.0-29B-Intent
92
+ - nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
93
  - empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF
94
+ - Qwen/Qwen3.6-35B-A3B
95
+ - google/gemma-4-E4B-it
96
  - ornith-ai/Ornith-1.5-9B-GGUF
97
+ - black-forest-labs/FLUX.2-dev
98
+ - DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
99
+ - black-forest-labs/flux-3-image-klein-base
100
  - BAAI/AREX-2
101
+ - unsloth/Qwen3.6-35B-A3B-GGUF
102
+ - lodestones/Chroma1-HD
103
+ - bartowski/Nanbeige_Nanbeige4.3-33B-GGUF
104
  - yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
105
+ - fastino/GLiDE
106
+ - peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP
107
  - meta-models/Muse-Glimmer-30B
 
 
108
  - nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
 
 
 
109
  - InternScience/Sage-A1.5-Q4_K_M-GGUF
 
 
 
 
 
 
 
 
 
 
110
  - unsloth/Qwen-Image-2.1-GGUF
111
+ - unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
112
+ - agentionai/Qwen3.8-Flash-Next-Gyro-Coder-GGUF
113
+ - KRAFTON/Raon-1-mini-preview-gguf
114
+ - nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
115
  - webbrain-one/Nanbeige4.3-33B-NVFP4
116
  - destined/hurston-1
117
  - unsloth/Ornith-1.5-122B-GGUF
118
  - GrootTeam/Groot-19B-A3B-261023-GGUF
119
  - Aratako/Drama-3-Japanese
 
 
 
 
 
 
 
120
  - ukisai/Swift-1.5-Qwen3.8-27B-GGUF
121
+ - nvidia/LocateAnything-3B
122
+ - Aleph-Alpha/Kolibri-1
123
+ - Cloudflare/clef-flash
124
+ - ornith-ai/Ornith-1.5-35B-A3B
125
+ - peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF
126
+ - XiaomiMiMo/MiMo-V2.6-Pro-RL
127
+ - datalab-to/chandra-ocr-2
128
  - JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF
129
+ - peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF
130
+ - deepseek-ai/DeepSeek-V4-Flash
131
  - google/gemma-4-26B-A4B-it
132
+ - unsloth/Qwen3.5-4B-GGUF
133
+ - Nanbeige/Nanbeige4.2-3B
134
+ - paperinstruments/Ultramarine-1-Flash
135
+ - LiquidAI/LFM2.5-24B-A2B
136
+ - google/medgemma-1.5-4b-it
137
  - inclusionAI/Ming-3.0-tts-tiny
 
 
138
  - Qwen/Qwen3-8B-GGUF
 
 
139
  - unsloth/Qwen3.5-9B-GGUF
140
  - fishaudio/s2-pro
 
 
 
 
141
  - Qwen/Qwen2.5-Coder-7B-Instruct-GGUF
 
142
  - stabilityai/stable-diffusion-3.5-medium
143
  - RavichandranJ/Dolphin3-Cyber-8B-GGUF
 
 
144
  - google/gemma-4-12B-it
145
+ - Qwen/Qwen3.8-2.4T-A95B
146
+ - LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GGUF
147
+ - tencent/Hy-Memory-30B-A3B
148
+ - bottlecapai/ThinkingCap-gemma-4-26B-A4B-it
149
+ - LiquidAI/d1-3B
150
+ - ibm-granite/granite-switch-4.1-30b
151
+ - abacusai/Smaug-Humanizer
152
+ - peasantsmith/DeepSeek-V4.1-Flash-1017-Maya-GGUF
153
+ - google/gemma-4-E2B-it
154
+ - empero-ai/Qwythos-9B-Claude-Mythos-5-1M
155
+ - Diffuspace/Clover-35B-A3B-Preview-GGUF
156
+ - RecursiveSI/flint-nvfp4-gguf
157
+ - ornith-ai/Ornith-1.5-35B-A3B-GGUF
158
+ - akhaliq/MOSS-Image-SFT-4-steps
159
  - ibm-granite/granite-switch-4.1-8b
160
+ - inclusionAI/Ling-3.1-flash-base
161
+ - nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16
162
  - kaushikvira/DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata
163
+ - ornith-ai/Ornith-1.5-9B
164
+ - Lightricks/LTX-2.5-Diffusers
165
+ - ceia-br/lumi-4b
166
+ - tencent/WeVisCut
167
+ - google/gemma-4-12B-it-qat-q4_0-gguf
168
+ - Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata
169
  - RecursiveSI/flint-int4-gguf
 
 
 
170
  - LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF
 
 
 
171
  - Qwen/Qwen3-4B-Instruct-2507
 
 
 
172
  - ornith-ai/Ornith-1.5-122B-GGUF
173
  - meta-llama/Llama-3.2-3B
174
+ - nvidia/Qwen3.8-27B-NVFP4
175
+ - deepseek-ai/DeepSeek-V4-Pro
176
+ - Qwen/Qwen3-Coder-Next
177
+ - unsloth/GLM-5.3-Flash-GGUF
178
+ - nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
179
+ - DogukanUrker/Nanbeige4.3-33B-GGUF
180
+ - ProCreations/Nanbeige4.3-33B-DFlash2
181
+ - unsloth/GLM-4.7-Flash-GGUF
182
+ - bartowski/HemmingwayAI_Hemmingway-1.5-GGUF
183
+ - empero-ai/Qwen3.8-9B-Distill-GGUF
184
+ - yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
185
+ - AtomicChat/Clover-35B-A3B-Preview-GGUF
186
+ - nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
187
+ - stealth-model/Qwen4
188
+ - XHToken/Spark-X2.6-4B-Base
189
+ - IsValorum/Flint-APEX-I-MiniPlus-V2.1-GGUF
190
  - microsoft/Sentiment-Analysis-7B
 
 
191
  - unsloth/MOSS-Image-SFT-GGUF
 
 
 
192
  - HuggingFaceBio/Carbon-X-GGUF
 
193
  - google/gemma-4-E4B
 
194
  - NousResearch/Hermes-3-Llama-3.1-8B
 
 
 
 
 
195
  - abenzerps/Nemotron-3.5-Bolt-E4B-GSQ-RCO-GGUF
 
 
196
  - ornith-ai/Ornith-1.5-122B-NVFP4
 
 
 
197
  - LiquidAI/LFM2.5-24B-A2B-GGUF
 
 
198
  - abenzerps/Spark-X2.6-4B-Quantized
 
199
  - bartowski/Spark-X2.6-4B-GGUF
 
 
200
  - inclusionAI/Ling-3.0-tiny
 
 
 
 
201
  - SuperLogic/Qwen3.8-27B-Flash-MTP-GGUF
202
+ - nvidia/NLD-Uni
203
+ - Qwen/Qwen-Image-Edit-2511
204
+ - stabilityai/stable-video-diffusion-img2vid-xt-1-1
205
+ - basecompute/Qwen3.8-27B-BaseQuant-V1
206
+ - Teriminal-RSI/Terminal-RSI-27B
207
+ - unsloth/LFM2.5-24B-A2B-GGUF
208
+ - kaitchup/Qwen3.8-27B-SLQ-EAR98
209
+ - diffbot/DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000
210
+ - unsloth/Qwen-Image-2.1-Turbo-GGUF
211
+ - poolside/Laguna-S-2.1
212
  - Wan-AI/Wan2.1-T2V-14B
213
  - YoSaNoo/Forge-1-Gemma-4-E2B
214
+ - DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF
215
+ - Qwen/Qwen2.5-Coder-3B-Instruct-GGUF
216
+ - incoai/Qwen3.8-27B-DFlash2
217
+ - zai-org/GLM-5.2
218
+ - jialinyyzz/humanizer-GGUF
219
  - inclusionAI/Ling-3.1-flash
220
+ - divagr1925/Qwen3.5-4B-Qwenputer-Filesystem
221
+ - empero-ai/Qwen3.8-35B-A3B-Distill
222
  ---
223
 
224
  # VRAM & GPU Cost Calculator
 
232
 
233
  ## Which models
234
 
235
+ Any public model on the Hub that publishes a parameter count. The search box lists 12,716 of them: the text, vision-language, image, video, speech and embedding models the Hub counted at 1,000 or more downloads in the 30 days before a build day from 2026-10-11 to 2026-10-31, plus the ones trending on those days. Left out of the list: models too small to need a rented GPU, adult and refusal-stripped fine-tunes, and builds for Apple silicon, CPUs or phones. Anything else is found through the Hub's own search as you type, or by pasting its `org/name`.
236
 
237
  ## How the memory is sized
238
 
catalog-more.js CHANGED
The diff for this file is too large to render. See raw diff
 
catalog.js CHANGED
The diff for this file is too large to render. See raw diff
 
catalog.meta.json CHANGED
@@ -1 +1 @@
1
- {"download_floor":1000,"built":"2026-10-30","since":"2026-10-11","models":12559,"buried":{"Qwen/Qwen3.8-27B":"2026-10-30","OpenMOSS-Team/MOSS-Image-SFT":"2026-10-30","Qwen/Qwen-Image-2.1":"2026-10-30","meta-llama/Meta-Llama-3-8B-Instruct":"2026-10-30","meta-llama/Llama-3.1-8B-Instruct":"2026-10-30","google/gemma-4-31B-it":"2026-10-30","black-forest-labs/FLUX.1-dev":"2026-10-30","krea/Krea-2-Turbo":"2026-10-30","Qwen/Qwen3.5-4B":"2026-10-30","black-forest-labs/FLUX.1-schnell":"2026-10-30","Qwen/Qwen3.5-9B":"2026-10-30","meta-llama/Llama-3.2-3B-Instruct":"2026-10-30","openai/gpt-oss-120b":"2026-10-30","meta-llama/Llama-3.1-8B":"2026-10-30","black-forest-labs/FLUX.2-klein-9B":"2026-10-30","Viggle/Qwen-Image-2.1-viggle-turbo":"2026-10-30","openai/gpt-oss-20b":"2026-10-30","Lightricks/LTX-Video":"2026-10-30","Tongyi-MAI/Z-Image-Turbo":"2026-10-30","deepseek-ai/DeepSeek-R1":"2026-10-30","stabilityai/stable-diffusion-xl-base-1.0":"2026-10-30","Qwen/Qwen3-8B":"2026-10-30","Qwen/Qwen3-14B":"2026-10-30","black-forest-labs/FLUX.2-klein-4B":"2026-10-30","meta-llama/Llama-2-7b-chat-hf":"2026-10-30","Qwen/Qwen2.5-7B-Instruct":"2026-10-30"}}
 
1
+ {"download_floor":1000,"built":"2026-10-31","since":"2026-10-11","models":12716,"buried":{"Qwen/Qwen3.8-27B":"2026-10-30","OpenMOSS-Team/MOSS-Image-SFT":"2026-10-30","Qwen/Qwen-Image-2.1":"2026-10-30","meta-llama/Meta-Llama-3-8B-Instruct":"2026-10-30","meta-llama/Llama-3.1-8B-Instruct":"2026-10-30","google/gemma-4-31B-it":"2026-10-30","black-forest-labs/FLUX.1-dev":"2026-10-30","krea/Krea-2-Turbo":"2026-10-30","Qwen/Qwen3.5-4B":"2026-10-30","black-forest-labs/FLUX.1-schnell":"2026-10-30","Qwen/Qwen3.5-9B":"2026-10-30","meta-llama/Llama-3.2-3B-Instruct":"2026-10-30","openai/gpt-oss-120b":"2026-10-30","meta-llama/Llama-3.1-8B":"2026-10-30","black-forest-labs/FLUX.2-klein-9B":"2026-10-30","Viggle/Qwen-Image-2.1-viggle-turbo":"2026-10-30","openai/gpt-oss-20b":"2026-10-30","Lightricks/LTX-Video":"2026-10-30","Tongyi-MAI/Z-Image-Turbo":"2026-10-30","deepseek-ai/DeepSeek-R1":"2026-10-30","stabilityai/stable-diffusion-xl-base-1.0":"2026-10-30","Qwen/Qwen3-8B":"2026-10-30","Qwen/Qwen3-14B":"2026-10-30","black-forest-labs/FLUX.2-klein-4B":"2026-10-30","meta-llama/Llama-2-7b-chat-hf":"2026-10-30","Qwen/Qwen2.5-7B-Instruct":"2026-10-30","stabilityai/stable-diffusion-3.5-large":"2026-10-31","meta-llama/Llama-2-7b-hf":"2026-10-31"}}