license, base_model, tags, language, library_name, pipeline_tag

license	base_model	tags	language	library_name	pipeline_tag
apache-2.0	wangzhang/gpt-oss-20b-abliterated	abliterated uncensored moe gpt-oss gguf llama.cpp abliterix	en zh	llama.cpp	text-generation

gpt-oss-20b-abliterated — GGUF quants

GGUF builds of wangzhang/gpt-oss-20b-abliterated for running in llama.cpp, Ollama, LM Studio, KoboldCpp, text-generation-webui, and anything else that speaks GGUF.

Files

File	Quant	Size	Use case
gpt-oss-20b-abliterated-bf16.gguf	BF16 (full precision)	~42 GB	Reference quality. Requires 48+ GB VRAM (or large CPU RAM). Use if you care about identical behaviour to the HF checkpoint.
gpt-oss-20b-abliterated-q8_0.gguf	Q8_0 (8-bit, GGUF's FP8-equivalent)	~22 GB	Near-lossless vs BF16. Runs comfortably on a single 24 GB GPU. Recommended default.
gpt-oss-20b-abliterated-q4_k_m.gguf	Q4_K_M (4-bit k-quant, M profile)	~15 GB	Best size / quality trade-off at 4-bit. Fits on 16 GB VRAM or modest CPU setups.

GGUF does not have a native FP8 type; Q8_0 is the standard 8-bit path and is what every publisher on the Hub ships as "fp8 equivalent". Q4_K_M is the best 4-bit choice for this model — Q4_0 is noticeably worse on MoE models, Q5_K_M is ~25% larger for diminishing returns.

Source

Built from the merged BF16 weights of the abliteration run, not from the original MXFP4 (since the abliteration required dequantising experts to BF16 to enable direct weight editing). The BF16 → GGUF conversion uses llama.cpp's convert_hf_to_gguf.py; the quantised variants use llama-quantize.

All three files are functionally identical to the BF16 HF checkpoint at Q8_0 fidelity; Q4_K_M adds minor additional quantisation noise but keeps the abliteration effect intact (spot-checked on the same 15-prompt EN/ZH jailbreak set used for the HF release).

Quick start (llama.cpp)

# Download one quant:
huggingface-cli download wangzhang/gpt-oss-20b-abliterated-GGUF \
    gpt-oss-20b-abliterated-q4_k_m.gguf --local-dir ./

# Run with gpt-oss's harmony chat template (bundled in the GGUF):
./llama-cli -m gpt-oss-20b-abliterated-q4_k_m.gguf \
    -cnv -p "You are a helpful assistant." \
    --reasoning-budget 0 \
    -n 512

Quick start (Ollama)

ollama pull hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M
ollama run hf.co/wangzhang/gpt-oss-20b-abliterated-GGUF:Q4_K_M

What this actually is

The HF checkpoint this is built from is an "abliterated" variant of gpt-oss-20b — refusals on harmful prompts have been suppressed via direct weight editing and MoE router suppression. Refusal rate on a 100-prompt held-out eval drops from 97/100 (base) to 6/100 (abliterated). See the base HF card for metrics, method, and honest limitations.

These GGUFs inherit that behaviour. They are intended for authorised AI-safety research, red-teaming, and mechanism analysis — not for producing or distributing harmful content. The apache-2.0 license of the upstream OpenAI gpt-oss release applies.

Acknowledgments

• openai/gpt-oss-20b — base model
• ggerganov/llama.cpp — GGUF format and quantisation kernels
• abliterix — abliteration pipeline (Heretic derivative)