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 Blog…Qwen3-30B Similar experiments were run on mixture-of-experts (MoE) models, with results for Qwen3-30B showing matching accuracy curves. FP8 achieves similar accuracy to BF16. Speed gain is being investigated…
…시간(TTFT)은 1.3배 단축된 기준을 적용하여 높은 상호작용이 필요한 배포 환경을 반영합 니다. Qwen3-VL-235B-A22B : 총 2,350억 개의 파라미터를 가진 시각-언어 모델(VLM)입니다. MLPerf Inference…
…The strongest result was on Qwen3-0.6B , where the pass rate increased from 16.7% to 59.2%. Why Bash Agentic systems increasingly use language models to generate code and commands…
…Nemotron-3-Super-120B-A12B-NVFP4 on 4XB200 with TP=4, with --enable-anthropic-api , --strip-anthropic-preamble , --enable-streaming-tool-dispatch , the nemotron_deci reasoning parser, and the qwen3_coder tool…
…For example, on HuggingFace, developers can find ready-to-deploy NVFP4 versions such as Llama 3.3 70B , FLUX.2 , DeepSeek-R1-0528, Kimi-K2-Thinking, Qwen3-235B-A22B, and NVIDIA Nemotron…
…Several models that are popular in the context of OpenClaw—including Qwen3.5 397B, GLM 5, and MiniMax M2.5 230B—can benefit from stacking multiple DGX Spark units, increasing the available…
…This range enables evaluating fractional allocation across workloads with different memory footprints. Notably, the largest model (Qwen3-14B) occupies only ~35% of one NVIDIA H100 NVL GPU 80 GB capacity, illustrating why…
…Running the Qwen3-VL-30B-A3B-Instruct-FP8 multimodal model on NVIDIA GB200, Dynamo’s embedding cache accelerated time to first token (TTFT) by up to 30% and throughput by up to…