Inference benchmarks (BF16 vs NVFP4) - a M3mop1 Collection

M3mop1 's Collections

Inference benchmarks (BF16 vs NVFP4)

Inference benchmarks (BF16 vs NVFP4)

updated 8 days ago

nota-ai/Nemotron-3.5-Lightning-30B-A3B-Nota-Ternary-MLX-1014

Text Generation • 33B • Updated 10 days ago • 1.59k • 37
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Text Generation • 32B • Updated Aug 24 • 743k • • 246
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

Text Generation • 18B • Updated Sep 10 • 922k • 472