Ornstein3.6-35B-A3B-RYS-GGUF

Ornstein3.6-35B-A3B-RYS-GGUF

GGUF quantizations of DJLougen/Ornstein3.6-35B-A3B-RYS — the RYS-enhanced Ornstein fine-tune with layer 10 duplicated for a +49% reasoning improvement.

Full-precision model: DJLougen/Ornstein3.6-35B-A3B-RYS | Uncensored version: DJLougen/Ornstein3.6-35B-A3B-RYS-SABER

Support This Work

I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. All training compute is self-funded — balancing GPU costs against a student budget. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.

Support on Ko-fi

---

Available Quantizations

Model Details

• Architecture: Qwen 3.6 MoE (35B total, ~3B active per token)
• Layers: 41 (40 original + 1 RYS-duplicated layer 10)
• Context: 262,144 tokens
• RYS improvement: +139% math, +7.2% instruction following, +49% combined

Usage

llama.cpp

llama-cli -m Ornstein3.6-35B-A3B-RYS-Q4_K_M.gguf -p "Your prompt here" -ngl 99

Ollama

ollama run hf.co/DJLougen/Ornstein3.6-35B-A3B-RYS-GGUF:Q4_K_M

License

Apache 2.0