Qwen3 Next 80B A3B Instruct NVFP4 Quantized version of Qwen/Qwen3 Next 80B A3B Instruct using LLM Compressor and the NVFP4 (E2M1 + E4M3) format. This time it actually works! We think This should be the start of a new series of hopefully optimal NVFP4 quantizations as capable cards continue to grow out in the wild. Model Summary Property Value Base model Qwen/Qwen3 Next 80B A3B Instruct Quantization NVFP4 (FP4 microscaling, block = 16, scale = E4M3) Method Post Training Quantization with LLM Compressor Toolchain LLM Compressor Hardware target NVIDIA Blackwell (Untested on RTX cards) / GB200 Tensor Cores Precision Weights & activations = FP4 • Scales = FP8 (E4M3) Maintainer RESMP.DEV Description This model is a drop in replacement for Qwen/Qwen3 Next 80B A3B Instruct that runs in NVFP4 precision Accuracy remains within ≈ 1 % of the FP8 baseline on standard reasoning and coding benchmarks.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy