Qwen3.5 35B A3B NVFP4 EU AI Act Compliance Profile

AxionML Qwen3.5-35B-A3B-NVFP4

Developed by AxionML for open-source serving and deployment use cases. Part of AxionML's effort to provide ready-to-serve quantized models for the community.

This is an NVFP4-quantized version of Qwen/Qwen3.5-35B-A3B (35B (3B active) parameters), quantized using NVIDIA TensorRT Model Optimizer. Weights and activations of linear layers are quantized to FP4, reducing disk size and GPU memory by ~4x compared to BF16.

About NVFP4 quantization: NVFP4 on Blackwell couples a compact E2M1 FP4 codebook with blockwise FP8 (E4M3) scaling over 16-element micro-blocks, so that 4-bit stored values remain numerically useful for neural-network computation. The E2M1 codebook provides a small, nonuniform set of representable magnitudes up to ±6 and relies on saturating behavior rather than IEEE NaN/Inf encodings to maximize usable range per bit. Using an FP8 block scale (rather than power-of-two-only E8M0) enables fractional scales and error-minimizing scale selection strategies such as dual-pass evaluation comparing "map max to 6" versus "map max to 4 with clipping." On Blackwell Tensor Cores, native FP4 multipliers exploit E2M1 simplicity to reduce multiplier area while higher-precision FP32 accumulation protects dot-product accuracy.

Ready for commercial and non-commercial use under Apache 2.0.

[!Tip] For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Alibaba Cloud Model Studio.

In particular, Qwen3.5-Flash is the hosted version corresponding to Qwen3.5-35B-A3B with more production features, e.g., 1M context length by default and official built-in tools. For more information, please refer to the [User Guide](https://www.aliba

Your obligations as a Qwen3.5 35B A3B NVFP4 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library

Base Model