GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pqhaz
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
pqhaz
Model Tree
pqhaz/apex-flash-1-heretic-v2
Input Modalities
Output Modalities
Supported Functionality
NVFP4 quantization of pqhaz/apex-flash-1-heretic-v2: modelopt weight-only layout, routed experts only (gate/up/down projections, block size 16), everything else left in BF16. Tensor names, shard assignment and quantization_config are the same as in pqhaz/apex-flash-1-abliterated-NVFP4, so it is a drop-in replacement for that checkpoint.
Produced with nvfp4.py (included). The converter was checked against a shard of the earlier NVFP4 repo, converting the same source weights: packed weights and both scales came out bit-identical on the 25 expert tensors sampled.
See the BF16 repository for what was changed and how it was measured; ablation.json holds the exact parameter set. This quantization itself has not been evaluated.
Intended for authorized security research in environments the researcher owns or has permission to test.