OBLITERATUS / text-generation updated 3 weeks ago

Ornith-1.5-9B-OBLITERATED

Abliterated version of Ornith-1.5-9B by OBLITERATUS. Safety alignment removed via precision abliteration surgery — the model responds to most prompts without refusal.

Params
9.7 B
Context
Downloads 30d
359 K
Likes
73
Commercial use: allowed mit Not gated GGUF · SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
359 K228 K
Sep 11Sep 14Sep 17Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Ornith-1.5-9B-OBLITERATED-Q2_K.gguf Q2_K 3.9 GB 6.3 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-Q3_K_M.gguf Q3_K_M 4.7 GB 7.2 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-IQ4_XS.gguf IQ4_XS 5.4 GB 7.8 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-Q4_K_M.gguf Q4_K_M 5.8 GB 8.3 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-Q5_K_M.gguf Q5_K_M 6.6 GB 9.3 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-Q6_K.gguf Q6_K 7.6 GB 10.3 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-Q8_0.gguf Q8_0 9.8 GB 12.7 GB ✅ Runs comfortably
Ornith-1.5-9B-OBLITERATED-bf16.gguf GGUF 18.4 GB 22.2 GB ⚠️ Tight — reduce context
model.safetensors bf16 19.3 GB 23.2 GB ⚠️ Tight — reduce context
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_K_M
$ ollama run ornith-1-5-9b-obliterated

# pin the quantization explicitly
$ ollama run ornith-1-5-9b-obliterated-q4_k_m
est. VRAM 8.3 GBon RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3_5ForConditionalGeneration
Parameters
9.7 B
Tensor type
BF16
Licence
mit
First seen on the Hub
2026-08-27
Base model
Ornith-1.5-9B
Training datasets
undisclosed
Added to our catalog
2026-09-11

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model