Inference Providers
Active filters: fp4
AlekseyCalvin/QWEN_IMAGE_fp4_w_AbliteratedTE_Diffusers
Text-to-Image
• Updated • 114
• 8
imgailab/flux1-trtx-dev-fp4-blackwell
Updated • 7
• 1
imgailab/flux1-trtx-schnell-fp4-blackwell
Updated • 6
• 1
llmat/Mistral-7B-Instruct-v0.3-NVFP4
Text Generation
• 4B • Updated • 12
llmat/Mistral-Small-Instruct-2409-NVFP4
Text Generation
• 13B • Updated • 8
2imi9/gpt-oss-20B-NVFP4A16-BF16
Text Generation
• 21B • Updated • 498
• 4
xxrjun/DeepSeek-R1-0528-FP4
394B • Updated • 6
Sunbird/Sunflower-14B-4bit-fp4-bnb
Text Generation
• 15B • Updated • 2
Sunbird/Sunflower-32B-4bit-fp4-bnb
Text Generation
• 33B • Updated • 31
RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
Text Generation
• 133B • Updated • 4.78k
• 15
RedHatAI/Llama-3.1-8B-Instruct-NVFP4
Text Generation
• 5B • Updated • 19.5k
• 1
Text Generation
• 9B • Updated • 59.5k
RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4
Text Generation
• 14B • Updated • 49k
• 7
RedHatAI/Llama-4-Maverick-17B-128E-Instruct-NVFP4
Text Generation
• 229B • Updated • 375
• 5
RedHatAI/Qwen3-235B-A22B-NVFP4
Text Generation
• 136B • Updated • 100
• 1
RedHatAI/Qwen3-235B-A22B-Instruct-2507-NVFP4
Text Generation
• 136B • Updated • 778
• 4
prithivMLmods/Nanonets-OCR2-3B-AWQ-nvfp4
Image-Text-to-Text
• 3B • Updated • 26
nvidia/Kimi-K2-Thinking-NVFP4
Text Generation
• Updated • 25.4k
• 30
eousphoros/DeepSeek-V3.2-NVFP4
Text Generation
• 387B • Updated • 24
• 5
trithemius/Velvet-14B-nvfp4
8B • Updated • 2
Text Generation
• 199B • Updated • 49
josephdowling10/Mixtral-8x7B-Instruct-v0.1-NVFP4
Text Generation
• 23B • Updated • 26
Shifusen/L3.3-70B-Magnum-v4-SE-NVFP4
Text Generation
• 41B • Updated • 9
Firworks/Snowpiercer-15B-v4-nvfp4
9B • Updated • 6
cybermotaz/nemotron3-nano-nvfp4-w4a16
Text Generation
• 18B • Updated • 11.6k
• 14
Shifusen/Strawberrylemonade-L3-70B-v1.2-NVFP4
Text Generation
• 41B • Updated • 3
cybermotaz/qwen3-vl-2b-thinking-nvfp4-w4a16
Image-Text-to-Text
• 2B • Updated • 7
• 1
cybermotaz/qwen3-vl-4b-thinking-nvfp4-w4a16
Image-Text-to-Text
• 3B • Updated • 9
• 1
cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16
Image-Text-to-Text
• 5B • Updated • 240
• 2
Shifusen/72B-Qwen2.5-Kunou-v1-NVFP4
Text Generation
• 42B • Updated • 10