Qwen/Qwen3.5-35B-A3B-FP8
Image-Text-to-Text • 36B • Updated • 1.06M • 152
try-outs
Note Occupies about 100GB. Seeing about 20 tk/s. Builds a simple coding project autonomously, but struggles to stay unstuck when making semi-complicated edits. Had to use /goal aggressively to get any subsequent output from it.
deepreinforce-ai/Ornith-1.0-35B-FP8
Text Generation • 35B • Updated • 395k • 76Note Occupies about 100GB. Seeing 6-7 tk/s.
-
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4
Text Generation • 19B • Updated • 115k • 83 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 27B • Updated • 14.2M • • 1.27k -
cyankiwi/MiniMax-M2.7-AWQ-4bit
Text Generation • 37B • Updated • 44.6k • 41 -
nsfwthrowitaway69/Venus-103b-v1.0
Text Generation • 103B • Updated • 3 • 16 -
AxionML/Qwen3.5-122B-A10B-NVFP4
Image-Text-to-Text • 62B • Updated • 251 • 7 -
nvidia/MiniMax-M2.7-NVFP4
Text Generation • 116B • Updated • 79.9k • 64