Tracked topic
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
Experimental results for pruning and distillation from Qwen3 8B using Model Optimizer show that Qwen3 Depth Pruned 6B model is 30% faster than the Qwen3 4B model, and it also performs better on the MMLU (Massive Multitask Language Understanding) benchmark. Depth pruning was applied to reduce the model from 36 to 24 layers, resulting in a 6B model, using one NVIDIA H100 80 GB HBM3. The Pruned model is distilled from Qwen3-8B using the OptimalScale/ClimbMix data processed from nvidia/ClimbMix pretraining dataset. The experiment uses 25% of the data, which is approximately 90B tokens. Distillatio
Pruning and Distilling LLMs Using NVIDIA TensorRT Model Optimizer | NVIDIA Technical BlogAgentic AI / Generative AI Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints Feb 27, 2026 By Anu Srivastava Discuss (0) Discuss (0) L T F R E…
…torchrun --nproc_per_node 2 /opt/NeMo/scripts/llm/gpt_prune.py \ --devices 2 \ --pp_size 2 \ --restore_path Qwen3-8B-nemo \ --legacy_ckpt \ --save_path Qwen3-8B-nemo-width-pruned \ --seq…
…CUDA-Enabled GPU or CPU Nemotron 3 Nano 4B Nemotron 2 Nano 9B Qwen3-0.6B Qwen3-4B Qwen3 8B RAG - Embed Local GGML CUDA-Enabled GPU or CPU E5 Large Unsupervised…
Developer Tools & Techniques Build Next-Gen Physical AI with Edge‑First LLMs for Autonomous Vehicles and Robotics NVIDIA TensorRT Edge‑LLM introduces support for MoEs, Cosmos Reason 2, and Qwen3-TTS/ASR…
…deploying Qwen3-32B with NVFP4 quantization across 64 NVIDIA B200 GPUs, with target SLAs of 1000ms time-to-first-token (TTFT) and 15ms time-per-output-token (TPOT). Using a single command…
…In this case, Qwen3-32B is the base reasoning modeling that is fine-tuned for telco NOC workflows using the following design principles: Focusing on a small number of high‑impact faults…
…Muon training performance on NVIDIA GB300 NVL72 Table 1 summarizes training throughput of the Kimi K2 and Qwen3 30B models with Muon and the AdamW optimizer on the NVIDIA GB300 NVL72 system…
…The Qwen3-VL vision-language submission used the vLLM open source framework, showing how the community is rapidly building advanced multimodal optimizations to accelerate image-heavy inference workloads on the latest GPUs…
…In tests with Llama 3.1 8B and Qwen3-8B, running at ~50% sparsity resulted in near-lossless accuracy across most tasks. Danger zone: Pushing sparsity beyond 60% often leads to sharp…
…80GB Qwen3 30B a3B 1.2 9,058 tokens/sec/gpu 16x H100 NVIDIA DGX H100 nemo:26.02.01 4096 1 2 1 8 FP8 1024 H100-SXM5-80GB Qwen3 235B…