GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
HarimxChoi
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
HarimxChoi
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| Component | Format |
|---|---|
| Text projections | signed Hadamard + block-GPTQ INT3 |
| Weak columns | Output-Fisher selected BF16 recovery |
| Token embedding | group-128 INT4 |
| Vision weights | group-128 INT4 |
| Full-model packed-equivalent rate | 3.6912 bpw |
The repository stores the quantized values in BF16-compatible safetensors for direct Transformers loading. The bpw value is the analytical packed payload including codes, scales, recovery values, and column indices.
| Scope | Metric | Result |
|---|---|---|
| Text backbone | WikiText-2 PPL ↓ | 9.2494 |
| Text backbone | ARC-Challenge, 299 ↑ | 46.15 |
| Text backbone | MMLU, 13,943 ↑ | 38.13 |
| Full VLM | ChartQA-128 exact ↑ | 44.53 |
| Full VLM | ChartQA-128 relaxed ↑ | 53.91 |
Qwen3.5 currently requires the latest Transformers main branch:
bash
pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"
python
import torchfrom transformers import AutoModelForImageTextToText, AutoProcessormodel_id = "HarimxChoi/WarpQuant-Qwen3.5-4B-R16E4V4"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained(model_id,torch_dtype=torch.bfloat16,device_map="auto",)
bibtex
@misc{choi2026warpquant,author = {Harim Choi},title = {WarpQuant: Dual-Domain LLM Quantization via Hadamard Rotation and Output-Fisher Sensitivity},year = {2026},url = {https://harimxchoi.github.io/projects/warpquant/}}