# Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF

weighted/imatrix quants of https://huggingface.co/DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED

- **Kind:** model (Hugging Face)
- **Hugging Face:** https://huggingface.co/mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF
- **Owner:** mradermacher (https://forefy.com/u/hf/mradermacher)
- **Parameters:** 9.0B
- **Context:** 262144 tokens
- **License:** apache-2.0
- **Focus:** defensive
- **Architecture:** Qwen3_5ForCausalLM
- **Pinned revision:** `5936e88f1885b856b54520c372f2cd41e71819fd`
- **Page:** https://forefy.com/models/fbf2cfd1-4ae9-56a9-9744-d97da7ec19c0
- **API (JSON):** https://forefy.com/api/asr/models/fbf2cfd1-4ae9-56a9-9744-d97da7ec19c0

## What was done to it

- obliteratus (declared evidence)
- quantized (declared evidence, from DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED)

## Lineage

ornith-ai/Ornith-1.5-9B → OBLITERATUS/Ornith-1.5-9B-OBLITERATED → DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED → mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF

## Checks (repo at the pinned revision; not a behavior test)

- **Identity** [pass]: No lookalike name or conflicting provenance
- **Weights format** [pass]: GGUF only, nothing runs on load
- **Pickle files** [pass]: None.
- **Remote code** [pass]: None
- **Chat template** [pass]: Same as DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED's
- **Refusals modified** [info]: Yes: OBLITERATUS (declared)
- **License** [pass]: apache-2.0
- **Lineage** [pass]: Derives from DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED
- **Model card** [warn]: 4 of 6, missing evaluation results, intended use and limitations
- **GGUF headers** [pass]: 2 file(s) parsed, well-formed

## Variants

- Q6_K (gguf, 7.4 GB)
- Q5_K_M (gguf, 6.5 GB)
- Q5_K_S (gguf, 6.3 GB)
- Q4_1 (gguf, 5.8 GB)
- Q4_K_M (gguf, 5.6 GB)
- IQ4_NL (gguf, 5.4 GB)
- Q4_K_S (gguf, 5.4 GB)
- Q4_0 (gguf, 5.3 GB)
- IQ4_XS (gguf, 5.2 GB)
- Q3_K_L (gguf, 4.9 GB)
- Q3_K_M (gguf, 4.6 GB)
- IQ3_M (gguf, 4.4 GB)
- IQ3_S (gguf, 4.4 GB)
- Q3_K_S (gguf, 4.3 GB)
- IQ3_XS (gguf, 4.2 GB)
- IQ3_XXS (gguf, 3.9 GB)
- Q2_K (gguf, 3.8 GB)
- Q2_K_S (gguf, 3.7 GB)
- IQ2_M (gguf, 3.6 GB)
- IQ2_S (gguf, 3.4 GB)
- IQ2_XS (gguf, 3.3 GB)
- IQ2_XXS (gguf, 3.1 GB)
- IQ1_M (gguf, 2.9 GB)
- IQ1_S (gguf, 2.7 GB)
- Cyber-Ornith-1.5-9B-OBLITERATED.imatrix (gguf, 0.0 GB)

## Run it