JC1DA/Qwen3.8-27B-DavidAU-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-INT4-W4A16
134.2k
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU (W4A16)
W4A16 GPTQ quantization of Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU using AutoRound with GPTQ group size 128.
Quantization Details
Model size: ~19GB (vs ~54GB FP16) — 65% reduction
Benchmark Comparison: W4A16 vs FP16
Both versions benchmarked on identical hardware (NVIDIA A100 80GB) using vLLM 0.27.1.
Key findings:
- W4A16 matches or exceeds FP16 on all classification/generation benchmarks
- Perplexity difference is negligible (0.13%) — well within measurement variance
- No perceivable quality loss at 4-bit weights with 16-bit activations
Usage
Works with any framework supporting GPTQ/AutoRound checkpoints:
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-W4A16/DavidAU_Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-w4g128"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
torch_dtype="auto"
)Or via vLLM for high-throughput serving:
vllm serve DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-W4A16/DavidAU_Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-w4g128 \
--dtype auto --tensor-parallel-size 1Model Card
See the FP16 original model card for full details on training methodology, stages, and capabilities.
This quantized version preserves all characteristics of the original:
- Heretic/uncensored output
- Strong reasoning and instruction following
- Reduced overthinking tokens
- Auto-variable thinking sizes
