AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF
Text Generation • 864k • Updated • 14.3k • 21
NVIDIA Nemotron 3.5 Uncensored
Nemotron 3.5 Bolt E4B, Super VL and Bolt 74B with the refusal direction projected out, baked into Atomic Dynamic GGUF builds.
Note Bolt E4B: refusals 94% to 1% (EN), 76% to 0% (RU); 2 baked builds 5.1-7.4 GB + 3.5 MB LoRA; harmless-prompt KL gate not met, disclosed
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF
Image-Text-to-Text • 124B • Updated • 9.67k • 7Note Super VL 120B-A12B: refusals 95% to 0% (EN), MMLU unchanged; 3 baked builds 56-87 GB
-
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF
Image-Text-to-Text • 74B • Updated • 18.7k • 15
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF-metrics
Viewer • Updated • 1.93k • 190Note Bolt E4B: screen, gates, directions, baked-file checks
-
AtomicChat/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Uncensored-GGUF-metrics
Viewer • Updated • 1.93k • 719 -
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF-metrics
Viewer • Updated • 1.93k • 841