Qwen3.5-27B-heretic-v2-autoround-w4a16 is a weight-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	AWQ / AutoRound
Source / base	`llmfan46/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-v2`
Intended task	`image-text-to-text`
License	the license declared in the repository files

What is included

*.safetensors (5 files)
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
processor_config.json
chat_template.jinja
quantization_config.json
Additional configuration, tokenizer, processor, or shard files (18 visible artifacts total)

Quick start

vLLM (AWQ-compatible runtimes)

bash

vllm serve groxaxo/Qwen3.5-27B-heretic-v2-autoround-w4a16 \
  --quantization awq_marlin \
  --dtype float16 \
  --trust-remote-code

The exact kernel and flags depend on the quantizer and architecture. Check the files and source model card before selecting a production serving configuration.

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.

This is a 4-bit AutoRound export of:

llmfan46/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-v2

Quantization settings

Method: AutoRound 0.9.2
Scheme: W4A16
Bits: 4
Group size: 128
Iterations: 200
Calibration seqlen: 512
Calibration samples: 64
Batch size: 1
Gradient accumulate steps: 8
Low GPU memory mode: enabled
Packing format: auto_round:auto_gptq

Artifact summary

Source size: 51G
Quantized size: 18G
Size reduction: 64.71%
Final export: 5 safetensor shards

AutoRound reported 400/607 modules quantized. The visual tower, many linear_attn.in_proj_a/b layers, and lm_head remained unquantized.

Perplexity benchmark

WikiText-2 test split, sliding-window next-token perplexity:

seq_len=512
stride=256
max_tokens=8192

Model	PPL	Tokens scored	Load time	Eval time
FP source	7.518735	8161	9.829s	106.855s
AutoRound W4A16	7.747804	8161	5.844s	42.065s

Degradation vs FP: +3.0466%

Loading with Transformers

python

from transformers import Qwen3_5ForConditionalGeneration, AutoTokenizer

model = Qwen3_5ForConditionalGeneration.from_pretrained(
    "PATH/TO/THIS/MODEL",
    device_map="auto",
    trust_remote_code=True,
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "PATH/TO/THIS/MODEL",
    trust_remote_code=True,
)

Loading with vLLM

bash

python -m vllm.entrypoints.openai.api_server \
  --model PATH/TO/THIS/MODEL \
  --quantization gptq \
  --tensor-parallel-size 2

Included benchmark/report artifacts

benchmark_summary.json
heretic_v2_fp_ppl.json
heretic_v2_quant_ppl.json
HERETIC_V2_QUANTIZATION_REPORT.md

Notes

The source model architecture is Qwen3_5ForConditionalGeneration.
Text-only evaluation was run through the internal language model path.
Please follow the original model's usage terms and license expectations.