Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
An uncensored / abliterated build of deepreinforce-ai/Ornith-1.0-35B — DeepReinforce's state-of-the-art agentic-coding MoE — with refusal behavior removed while preserving capability.
Params
35.1 B
Context
—
Downloads 30d
211 K
Likes
29
Download history
daily snapshots · 37 days
▲ 158 K in the last 30 days (42.9%)
417 K211 K
Aug 23Sep 2Sep 12Sep 21
417 K180 K
Aug 16Aug 28Sep 9Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 70.2 GB | 83.0 GB | ❌ Won’t fit |
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$ curl -s https://aimodelscomparison.com/api/v1/models/ornith-1-0-35b-aeon-ultimate-uncensored-bf16
{
"hf_id": "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16",
"params_b": 35.11,
"context_length": null,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 210853,
"vram_estimates": [
{ "quant": "bf16", "gb": 83.0 }
],
"updated_at": "2026-08-16T01:00:35Z"
}
Specifications
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Parameters
- 35.1 B
- Tensor type
- BF16
- Licence
- mit
- First seen on the Hub
- 2026-06-27
- Base model
- Ornith-1.0-35B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-16
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model