-
-
-
-
-
-
Inference Providers
Active filters: fp8
ai-sage/GigaChat3-10B-A1.8B
Text Generation
• 11B • Updated
• 153k
• 65
Text-to-Image
• Updated
• 12.6k
• 41
unsloth/Ministral-3-3B-Instruct-2512-FP8
4B • Updated
• 146
• 1
mratsim/MiniMax-M2.1-FP8-INT4-AWQ
Text Generation
• Updated
• 284
• 39
marksverdhei/GLM-4.7-Flash-FP8
Text Generation
• Updated
• 90.3k
• 19
Sikaworld1990/gemma-3-12b-it-abliterated-sikaworld-high-fidelity-edition-Ltx-2
Text-to-Image
• Updated
• 4.97k
• 20
Image-Text-to-Text
• Updated
• 120k
• 259
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX-FP8
Image-Text-to-Text
• 4B • Updated
• 178
• 3
prithivMLmods/gemma-3-27b-it-abliterated-FP8
Image-Text-to-Text
• 27B • Updated
• 95
• 2
EliasOenal/MiniMax-M2.5-Hybrid-AWQ-W4A16G128-Attn-fp8_e4m3-KV-fp8_e4m3
Text Generation
• 34B • Updated
• 560
• 12
cerebras/MiniMax-M2.5-REAP-139B-A10B
Text Generation
• 139B • Updated
• 5.46k
• 21
cerebras/MiniMax-M2.5-REAP-172B-A10B
Text Generation
• 173B • Updated
• 1.55k
• 24
skyblanket/glm5-abliterated-fp8
744B • Updated
• 214
• 1
LiconStudio/VBVR-wan2.2-comfy-bf16
Updated
• 7.03k
• 22
edp1096/Huihui-Qwen3.5-35B-A3B-abliterated-FP8
Image-Text-to-Text
• 36B • Updated
• 4.99k
• 4
zswll2/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED-fp8-sglang
Updated
• 84
• 1
inference-optimization/sarvam-30b-FP8-Dynamic
Text Generation
• 32B • Updated
• 102
• 1
RedHatAI/sarvam-30b-FP8-Dynamic
Text Generation
• 32B • Updated
• 113
• 1
RedHatAI/sarvam-105b-FP8-Dynamic
Text Generation
• 106B • Updated
• 150
• 1
FriendliAI/Meta-Llama-3-8B-Instruct-fp8
Text Generation
• 8B • Updated
• 27
• 2
RedHatAI/Meta-Llama-3-8B-Instruct-FP8
Text Generation
• Updated
• 6.86k
• • 24
RedHatAI/Mixtral-8x7B-Instruct-v0.1-AutoFP8
Text Generation
• 47B • Updated
• 3
• 3
anyisalin/Meta-Llama-3-8B-Instruct-FP8
Text Generation
• 8B • Updated
• 7
anyisalin/Meta-Llama-3-8B-Instruct-FP8-D
Text Generation
• 8B • Updated
• 4
anyisalin/lzlv_70b_fp16_hf-FP8-D
Text Generation
• 69B • Updated
• 1
anyisalin/Meta-Llama-3-70B-Instruct-FP8-D
Text Generation
• 71B • Updated
• 3
anyisalin/Mixtral-8x7B-Instruct-v0.1-FP8-D
Text Generation
• 47B • Updated
• 2
pcmoritz/Mixtral-8x7B-v0.1-fp8-act-scale
Text Generation
• 47B • Updated
• 2
anyisalin/Meta-Llama-3-70B-Instruct-FP8
Text Generation
• 71B • Updated
• 2