DeepReinforce · 122B (10B active) · Mixture of Experts
Largest Ornith 1.5 — self-improving agentic coding MoE built for single-GPU deployment Check if your GPU or Mac can run Ornith 1.5 122B locally — 68.2 GB min, 113.6 GB recommended.
2026-10256K context
Mixture of Experts
Total experts: 256
Active experts: 8
Active params: 10.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 39.6 GB | low | — |
| Q3_K_M | 3 | 55.2 GB | moderate | — |
| Q4_K_M | 4 | 63 GB | good | — |
| Q5_K_M | 5 | 78.6 GB | good | — |
| Q6_K | 6 | 94.2 GB | excellent | — |
| Q8_0 | 8 | 125.5 GB | excellent | — |
| F16 | 16 | 250.5 GB | lossless | — |
Can I run Ornith 1.5 122B locally?
- Can I run Ornith 1.5 122B locally?
- Ornith 1.5 122B needs about 68.2 GB of memory at a minimum and 113.6 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Ornith 1.5 122B need?
- At Q4_K_M, Ornith 1.5 122B uses about 63 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.