Model Optimizer

mentions 2 type Person feed RSS

// recent coverage 2 mentions

10:37

2026-06-18

dev.to

large-language-models

Qwen3.6-35B NVFP4 runs on one H100 — A100 owners are out

NVIDIA released Qwen3.6-35B-A3B-NVFP4, a post-training FP4-quantized variant of Alibaba's 35B MoE model that fits on a single H100 by reducing VRAM from ~71 GB to ~23 GB. The quantization targets weig…

18:27

2026-06-09

developer.nvidia.com

artificial-intelligence

Model Quantization: Turn FP8 Checkpoints into High-Performance Inference Engines with NVIDIA TensorRT

NVIDIA released a workflow for converting FP8-quantized CLIP model checkpoints into TensorRT engines, enabling faster inference and higher GPU throughput for production deployment. The process involve…

// co-occurs with top 8 entities

NVIDIA 2 TensorRT 1 CLIP 1 ONNX 1 TensorRT-LLM 1 ModelOpt 1 Alibaba 1 Qwen3.6-35B-A3B-NVFP4 1

// topics top 6 topics

ai infrastructure 2 artificial intelligence 1 machine learning 1 neural networks 1 ai tools 1 large language models 1