Will this model run on your hardware?
Can I run Ornith-1.5-35B-A3B locally?
- 36B parameters (3.0B active, MoE)
- context up to 256K
- licence: mit
- Weights: ornith-ai/Ornith-1.5-35B-A3B · GGUF: bartowski/Ornith-1.5-35B-A3B-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 37.8 GB |
| Q6_K | 30.5 GB |
| Q5_K_M | 25.5 GB |
| Q4_K_M | 21.9 GB |
| Q3_K_M | 16.7 GB |
| Q2_K | 13.1 GB |
Run it locally
ollama run hf.co/bartowski/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
llama serve -hf bartowski/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
LM Studio: open bartowski/Ornith-1.5-35B-A3B-GGUF