Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER
27BQwenheretic
from DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
↓ 1.4M♥ 2.4K37 repos
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated is a Heretic-ablated variant of DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU, published on Hugging Face by cbert33. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in FP8 format, totalling 17.9K downloads.
Specification
- Model name
- Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated
- Source repository
- cbert33/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-FP8-KV-Calibrated
- Publisher
- cbert33
- Parameters
- 27B
- VRAM required
- ~17.2 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- FP8
- First indexed
- 4 Sept 2026
- Last updated
- 4 Sept 2026
Ablation technique
How Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“All credit goes to DavidAU. This is a W8A8 quant of his model with fp8 calibrated cache. Everything else on his model is untouched.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "cbert33/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-FP8-KV-Calibrated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve cbert33/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-FP8-KV-Calibrated --trust-remote-codeDownloads and variants (1)
The only published repository of Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated.
| Repository | Format | Downloads |
|---|---|---|
| cbert33/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-FP8-KV-Calibratedsource | FP8 | 17.9K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU, not added by ablation — at 27B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-KV-Calibrated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with cbert33, and does not independently verify publisher claims. See responsible use.