Downloads · 30 days
27
12% of all-time downloads
ethanfel/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic-FP8
Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic-FP8 is a image-text-to-text model from ethanfel. 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.
Native compressed-tensors FP8 checkpoint converted from gorbatjovy/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic at revision 3504178f8097e4a593cdb8c94ce6752037d41f91.
Downloads · 30 days
27
12% of all-time downloads
All-time downloads
227
Public
Parameters
27.8B
36.8 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors36.8 GB · 100%
How the weights are stored.
F8_E4M318.8B · 68%
From the Hugging Face model README
Native compressed-tensors FP8 checkpoint converted from
gorbatjovy/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic
at revision 3504178f8097e4a593cdb8c94ce6752037d41f91.
This conversion preserves the abliterated source model, its multimodal vision tower, and its restored Qwen3.5 MTP draft layer. The source model card reports 4 refusals out of 100 prompts and KL divergence 0.0074 for its Heretic 1.4 conversion.
compressed-tensors / FP8_BLOCKlm_head, vision tower, Gated DeltaNet
linear-attention layers, and MTP layersllmcompressor==0.9.0, compressed-tensors==0.13.0Do not force --quantization fp8: vLLM reads quantization_config and
automatically selects compressed-tensors.
Validated locally on an NVIDIA GeForce RTX 5090 (SM120) with vLLM 0.26.0, PyTorch 2.11.0, and CUDA 13.0:
CutlassFp8BlockScaledMMKernel for
CompressedTensorsW8A8Fp8.qwen3_coder: passed.See fp8-verification.json and SHA256SUMS for machine-readable results and
shard checksums.
vllm serve ethanfel/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic-FP8 \
--host 0.0.0.0 \
--port 8000 \
--served-model-name qwen3.6-27b-fable-heretic-fp8 \
--max-model-len 131072 \
--gpu-memory-utilization 0.90 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3 \
--speculative-config '{"method":"mtp","num_speculative_tokens":1}'
For clients such as ComfyUI OpenAI-compatible nodes, use:
Base URL: http://SERVER_IP:8000/v1
Model: qwen3.6-27b-fable-heretic-fp8
The checkpoint itself supports up to 262,144 tokens. The example deliberately
uses 131,072 to leave generous deployment headroom. A client must keep
input_tokens + max_tokens <= MAX_MODEL_LEN; do not request the entire
remaining context as output without reserving a margin for tokenizer
differences.
This checkpoint inherits the uncensored/abliterated behavior of its source and is not a safety-aligned model. Operators are responsible for access control, logging, applicable law, and any application-level safeguards required by their deployment.