PRISM abliterated variants of Qwen 3.5 122B-A10B — multimodal MoE with hybrid attention. PRO, LITE, and GGUF formats.
Eric PRO
Ex0bit
AI & ML interests
None yet
Recent Activity
liked a Space 1 day ago
Ex0bit/tensorbend updated a Space 11 days ago
Ex0bit/tensorbend published a Space 11 days ago
Ex0bit/tensorbendOrganizations
models 27
Ex0bit/jit-lora
Updated • 77
Ex0bit/Qwen3.5-PRISM-Dynamic-Quant-GGUF
Text Generation • 0.8B • Updated • 3.56k • 6
Ex0bit/Qwen3.5-122B-A10B-PRISM-PRO-GGUF
Image-Text-to-Text • 122B • Updated • 180 • 19
Ex0bit/Qwen3.5-122B-A10B-PRISM-LITE-GGUF
Image-Text-to-Text • 122B • Updated • 4.2k • 12
Ex0bit/Kimi-K2.5-PRISM
Image-Text-to-Text • 171B • Updated • 8
Ex0bit/Kimi-K2.5-PRISM-REAP-530B-A32B
Text Generation • 91B • Updated • 1.41k • 19
Ex0bit/Step-3.5-Flash-PRISM-PRO-NVFP4
111B • Updated • 18 • 1
Ex0bit/MiniMax-M2.5-PRISM-PRO-Tensors
229B • Updated • 2
Ex0bit/MiniMax-M2.5-PRISM-PRO
Text Generation • 229B • Updated • 463 • 15
Ex0bit/MiniMax-M2.5-PRISM-LITE
Text Generation • 229B • Updated • 1.04k • 3
datasets 0
None public yet