Downloads · 30 days
69
0% of all-time downloads
groxaxo/Qwen3.6-27B-abliterated-v2-GPTQ-Pro-FOEM-4bit-g128
Qwen3.6-27B-abliterated-v2-GPTQ-Pro-FOEM-4bit-g128 is a image-text-to-text model from groxaxo. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Qwen3.6-27B-abliterated-v2-GPTQ-Pro-FOEM-4bit-g128 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source evaluation, reproducible experimentation, an…
Downloads · 30 days
69
0% of all-time downloads
All-time downloads
45.8K
Public
Parameters
27.4B
18.7 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors18.7 GB · 100%
How the weights are stored.
I3224.3B · 89%
From the Hugging Face model README
Qwen3.6-27B-abliterated-v2-GPTQ-Pro-FOEM-4bit-g128 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.
| Field | Details |
|---|---|
| Format | GPTQ |
| Source / base | the source checkpoint identified in the repository metadata |
| Intended task | image-text-to-text |
| License | the license declared in the repository files |
*.safetensors (5 files)config.jsongeneration_config.jsontokenizer.jsontokenizer_config.jsonprocessor_config.jsonchat_template.jinjaquantize_config.jsonvllm serve groxaxo/Qwen3.6-27B-abliterated-v2-GPTQ-Pro-FOEM-4bit-g128 \
--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.
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.
<!-- polished-overview:end -->FOEM-enhanced GPTQ-Pro W4G128 export of Qwen3.6-27B-abliterated-v2.
lm_head remains BF16model.language_model.embed_tokens remains BF16The local artifact was checked to confirm:
visual tensors > 0lm_head is not quantizedembed_tokens is not quantizedThe source model was also validated locally with image input before quantization.
The stable local vLLM launch on this machine was:
setsid env \
CUDA_VISIBLE_DEVICES=0,1,4 \
CUDA_DEVICE_ORDER=PCI_BUS_ID \
OMP_NUM_THREADS=1 \
TOKENIZERS_PARALLELISM=false \
NCCL_P2P_DISABLE=1 \
NCCL_IB_DISABLE=1 \
NCCL_NET_GDR_DISABLE=1 \
NCCL_SHM_DISABLE=0 \
NCCL_CUMEM_HANDLE_DISABLE=1 \
PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True,max_split_size_mb:256 \
/home/op/venvs/vllm-qwen36/bin/vllm serve "/home/op/models/Qwen3.6-27B-abliterated-v2" \
--host 0.0.0.0 \
--port 8000 \
--tensor-parallel-size 1 \
--pipeline-parallel-size 3 \
--max-model-len 4096 \
--kv-cache-dtype fp8 \
--gpu-memory-utilization 0.98 \
--max-num-seqs 1 \
--reasoning-parser qwen3 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--trust-remote-code \
--served-model-name qwen36-27b-abliterated-v2 \
--disable-custom-all-reduce \
--generation-config vllm \
--enforce-eager \
--limit-mm-per-prompt '{"image":1}'
Notes:
--max-model-len 32144 did not fit KV cache on this host.chat_template_kwargs.enable_thinking=false was used to avoid spending the visible token budget in the reasoning channel.quantize_config.json records the GPTQ-Pro + FOEM configprocessor_config.json keeps the multimodal processor configmodel.safetensors.index.json and shard files contain the final export