-
-
-
-
-
-
Inference Providers
Active filters:
fp8
Text Generation
•
229B
•
Updated
•
179k
•
•
791
Text Generation
•
310B
•
Updated
•
24.7k
•
•
532
deepseek-ai/DeepSeek-V3.2
Text Generation
•
685B
•
Updated
•
113k
•
•
1.06k
unsloth/Qwen-Image-2512-FP8
Text-to-Image
•
Updated
•
17
Text Generation
•
685B
•
Updated
•
457k
•
•
12.9k
mistralai/Devstral-Small-2-24B-Instruct-2512
24B
•
Updated
•
216k
•
456
Text Generation
•
229B
•
Updated
•
121k
•
•
1.44k
mistralai/Ministral-3-3B-Instruct-2512
4B
•
Updated
•
178k
•
164
deepseek-ai/DeepSeek-Math-V2
Text Generation
•
685B
•
Updated
•
3.98k
•
675
mistralai/Ministral-3-8B-Instruct-2512
9B
•
Updated
•
34.7k
•
119
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation
•
685B
•
Updated
•
31.7k
•
629
moonshotai/Kimi-K2-Instruct
Text Generation
•
1T
•
Updated
•
68.4k
•
•
2.29k
mistralai/Ministral-3-14B-Instruct-2512
14B
•
Updated
•
332k
•
213
mistralai/Devstral-2-123B-Instruct-2512
125B
•
Updated
•
14.9k
•
255
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
24B
•
Updated
•
144k
•
69
moonshotai/Kimi-K2-Instruct-0905
Text Generation
•
1T
•
Updated
•
31.7k
•
•
648
Qwen/Qwen3-Next-80B-A3B-Instruct-FP8
Text Generation
•
81B
•
Updated
•
313k
•
71
XiaomiMiMo/MiMo-V2-Flash-Base
Text Generation
•
310B
•
Updated
•
584
•
36
Text Generation
•
229B
•
Updated
•
71
•
6
Qwen/Qwen3-4B-Instruct-2507-FP8
Text Generation
•
4B
•
Updated
•
46.5k
•
59
tngtech/DeepSeek-R1T-Chimera
Text Generation
•
685B
•
Updated
•
390
•
267
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Text Generation
•
480B
•
Updated
•
110k
•
•
141
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
Text Generation
•
235B
•
Updated
•
32.7k
•
76
Qwen/Qwen3-30B-A3B-Instruct-2507-FP8
Text Generation
•
31B
•
Updated
•
333k
•
102
Qwen/Qwen3-30B-A3B-Thinking-2507-FP8
Text Generation
•
31B
•
Updated
•
27.2k
•
55
Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8
Text Generation
•
31B
•
Updated
•
169k
•
128
deepseek-ai/DeepSeek-V3.1
Text Generation
•
685B
•
Updated
•
51.9k
•
•
810
deepseek-ai/DeepSeek-V3.2-Exp
Text Generation
•
685B
•
Updated
•
72.9k
•
•
930
Qwen/Qwen3-VL-30B-A3B-Instruct-FP8
Image-Text-to-Text
•
31B
•
Updated
•
155k
•
94
Qwen/Qwen3-VL-4B-Instruct-FP8
Image-Text-to-Text
•
5B
•
Updated
•
30k
•
44