license: mit
base_model: cantina-security/apex-flash-1-abliterated
base_model_relation: quantized
tags:

• glm5_next
• abliterated
• security-research
• nvfp4
• modelopt
  pipeline_tag: image-text-to-text
  library_name: transformers

apex-flash-1-abliterated-NVFP4

Weight-only NVFP4 quantization of cantina-security/apex-flash-1-abliterated (321B MoE, GLM-5.3-Flash architecture).
~195 GB, vs ~643 GB BF16 / ~328 GB FP8 (FP8 version).

Format

Same layout as dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 (modelopt quant_algo: NVFP4):

• Only the routed MoE experts (mlp.experts.*.{gate,up,down}_proj) are quantized: E2M1 values packed two per byte (U8),
  FP8 E4M3 weight_scale per 16 input elements, FP32 per-tensor weight_scale_2 (= amax / (6 * 448)).
• Weight-only: no input_scale, input_activations: null. Use a W4A16 MoE path (e.g. vLLM Marlin / b12x W4A16), not native W4A4 kernels.
• Everything else (attention, KDA, shared experts, dense MLPs, routers, MTP, vision) is BF16, unchanged from the source.
• Round-to-nearest, no calibration. Expert tensor relative error ~9% (typical for NVFP4); passthrough tensors are bit-identical to the source.

Notes

• From the upstream card: this abliterated variant has not undergone a separate evaluation; it is intended for authorized security research.
• This quantization has not been separately benchmarked. Not affiliated with Cantina Security or Z.AI.

License

MIT, inherited from the base model. Copyright (c) 2026 Z.AI Co., Ltd — see LICENSE.