Article
2
Manjunath Janardhan PRO
manjunathshiva
AI & ML interests
AI and LLM's
Recent Activity
liked a Space 20 days ago
pollen-robotics/microduck-simulator liked a model 20 days ago
RecursiveSI/flint-int4 updated a model 20 days ago
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3-g64Organizations
Open, calibrated System One decision models: typed choice/score/yes-no answers. 400M to 80B · PyTorch, MLX, GGUF, ONNX, vLLM · pip install opendecider
-
manjunathshiva/opendecider-nano
Zero-Shot Classification • 0.4B • Updated • 1.29k • 13 -
manjunathshiva/opendecider-nano-ONNX
Zero-Shot Classification • Updated • 2 -
OpenDecider demo
🎯2Typed decisions with calibrated probabilities, ~400M model
-
manjunathshiva/opendecider-small
Zero-Shot Classification • Updated • 260 • 3
Data-free 2/3/4-bit + 1.58-bit ternary MLX quants of big MoEs for Apple Silicon. pip install turboquant-mlx-full
-
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3a-tqTe-g64
Image-Text-to-Text • 9B • Updated • 454 -
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3-g64
Image-Text-to-Text • 14B • Updated • 535 -
manjunathshiva/Qwen3.8-Flash-Next-tq4a-tq2e-g64
Text Generation • 17B • Updated • 1k • 8 -
manjunathshiva/Qwen3.8-27B-tq4-g64
Image-Text-to-Text • 4B • Updated • 218 • 1
Open, calibrated System One decision models: typed choice/score/yes-no answers. 400M to 80B · PyTorch, MLX, GGUF, ONNX, vLLM · pip install opendecider
-
manjunathshiva/opendecider-nano
Zero-Shot Classification • 0.4B • Updated • 1.29k • 13 -
manjunathshiva/opendecider-nano-ONNX
Zero-Shot Classification • Updated • 2 -
OpenDecider demo
🎯2Typed decisions with calibrated probabilities, ~400M model
-
manjunathshiva/opendecider-small
Zero-Shot Classification • Updated • 260 • 3
Data-free 2/3/4-bit + 1.58-bit ternary MLX quants of big MoEs for Apple Silicon. pip install turboquant-mlx-full
-
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3a-tqTe-g64
Image-Text-to-Text • 9B • Updated • 454 -
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3-g64
Image-Text-to-Text • 14B • Updated • 535 -
manjunathshiva/Qwen3.8-Flash-Next-tq4a-tq2e-g64
Text Generation • 17B • Updated • 1k • 8 -
manjunathshiva/Qwen3.8-27B-tq4-g64
Image-Text-to-Text • 4B • Updated • 218 • 1
models 45
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3-g64
Image-Text-to-Text • 14B • Updated • 535
manjunathshiva/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-tq3a-tqTe-g64
Image-Text-to-Text • 9B • Updated • 454
manjunathshiva/Qwen3.6-35B-A3B-tq3a-tqTe-g64
Text Generation • 3B • Updated • 308 • 5
manjunathshiva/Qwen3-235B-A22B-Instruct-2507-tq3a-tqTe-g64
Text Generation • 16B • Updated • 106 • 1
manjunathshiva/Qwen3.5-122B-A10B-tq3a-tqTe-g64
Text Generation • 9B • Updated • 202 • 3
manjunathshiva/Qwen3.6-35B-A3B-tq3a-tqTe-down4-g64
Text Generation • 4B • Updated • 211 • 1
manjunathshiva/Laguna-S-2.1-tqTe-g64
Text Generation • 8B • Updated • 97
manjunathshiva/Qwen3.8-Flash-Next-tq4a-tq2e-g64
Text Generation • 17B • Updated • 1k • 8
manjunathshiva/Qwen3.8-27B-tq4-g64
Image-Text-to-Text • 4B • Updated • 218 • 1
manjunathshiva/Qwen3.8-27B-tq3-mini-g64
Image-Text-to-Text • 3B • Updated • 369 • 5