Academica/Academica-Qwen3-8B-3Bit-Heretic
018
Academica-Qwen3-8B-3Bit-Heretic
Qwen3-8B with Heretic refusal-direction ablation and Q2_K quantization.
Academica produced the ablated model and all three published quantizations. This 3-bit release balances memory use, throughput, and generation quality.
Model details
The measurements describe the published artifact on the stated hardware. Results can differ with prompts, runtimes, and sampling settings.
Files
qwen3-8b-heretic-q2_k.gguf: Q2_K model weights.
Use
from huggingface_hub import hf_hub_download
model_path = hf_hub_download(
repo_id="Academica/Academica-Qwen3-8B-3Bit-Heretic",
filename="qwen3-8b-heretic-q2_k.gguf",
)llama-server -m qwen3-8b-heretic-q2_k.gguf --host 0.0.0.0 --port 8080 -ngl 99Limitations
Q2_K compression can reduce accuracy relative to larger quantizations. Validate the model against the intended task and runtime.
The ablation reduces refusal behavior. It does not establish factual accuracy, safety, or suitability for regulated decisions.
