Qwen3.5-9B-Abliterated-Claude-4.6-Opus-gptq-w4a16 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source evaluation, reproducible experimentation, and compatible local or hosted inference workflows. The wording below is deliberately limited to what can be verified from this repository's metadata and artifacts.

The repository name identifies a behavior-modified or reduced-filtering lineage. That label describes the source or conversion history; it is not a guarantee of unrestricted behavior in every prompt or runtime. Test outputs carefully before sharing or deploying them.

At a glance

Field	Details
Format	GPTQ
Source / base	`huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated`
Intended task	`text-generation`
License	`other`

What is included

*.safetensors (2 files)
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
chat_template.jinja
quantization_config.json
Additional configuration, tokenizer, processor, or shard files (9 visible artifacts total)

Quick start

vLLM (documented configuration)

bash

vllm serve groxaxo/Qwen3.5-9B-Abliterated-Claude-4.6-Opus-gptq-w4a16 \
  --quantization gptq_marlin \
  --dtype float16 \
  --trust-remote-code

This command is taken from the repository documentation. Adjust tensor parallelism, context length, and cache settings to match your hardware and vLLM version.

Compatibility and responsible use

Use a runtime that explicitly supports this format, architecture, and modality.
Keep configuration, tokenizer, processor, projection, and weight files from the same revision together.
Review the source model card and license before redistribution or deployment.
Hardware needs depend on parameter count, context length, cache precision, quantization, and concurrency.
Report reproducible issues with the runtime version, hardware, launch command, and a minimal example.

Quantization or conversion changes numerical behavior, memory use, and throughput relative to the source checkpoint; validate quality on your own workload.

Generated outputs may be inaccurate or unsuitable for a given use case. Users are responsible for testing behavior, applying appropriate safeguards, and complying with applicable licenses and laws.

AutoRound quantization in GPTQ format (W4A16) of Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled. Calibrated with OpenCodeCal, group 64, sequence length 1024, norm 192, full attention in fp16.

Quantization Details

Quantization method: AutoRound (GPTQ format)
Bits/Config: W4A16 (group 64, seq 1024, norm 192, OpenCodeCal, full-attn fp16)
Base model: Qwen3.5-9B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled