nvfp4

NVlabs/Sana

+87

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

LongLive

+21

Long Video Gen / World Model / World Action Model (Embodied) Infrastructure

strata-nvfp4

+15

Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants (huihui abliterated, OrcaRouter) from Hugging Face. CPU experts on AVX-512 or AVX2 (+AVX-VNNI), all experts in RAM from 92 GB, a low-RAM mode below, vision, W4A8 prompts. Windows / CUDA 13.

auto-round

+8

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率，量化感知训练的精度

dgx-spark-qwen38

+7

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.

sglang-rtxpro6000

+7

Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.

v100-skinny

+3

Hand-written NVFP4 W4A16 CUDA kernels for Volta