Can Ornith 1.5 35B A3B run on the RTX 5080?
Yes. At 8K context the best fit is Q2_K, using about 13.2 GB of the 15.2 GB usable on the RTX 5080. Estimated speed ceiling: ~879 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 13.1 GB Fits | 13.2 GB Fits | 13.7 GB Tight | 15.6 GB No | 879 |
| 3-bit (Q3_K_M) • | 16.5 GB No | 16.6 GB No | 17.0 GB No | 18.9 GB No | — |
| 4-bit (Q4_K_M) • | 21.3 GB No | 21.4 GB No | 21.9 GB No | 23.7 GB No | — |
| 5-bit (Q5_K_M) • | 24.7 GB No | 24.8 GB No | 25.2 GB No | 27.1 GB No | — |
| 6-bit (Q6_K) • | 29.4 GB No | 29.5 GB No | 29.9 GB No | 31.8 GB No | — |
| 8-bit (Q8_0) • | 36.2 GB No | 36.2 GB No | 36.7 GB No | 38.6 GB No | — |
| 16-bit (F16/BF16) • | 67.1 GB No | 67.2 GB No | 67.7 GB No | 69.6 GB No | — |
• real GGUF file size from bartowski/Ornith-1.5-35B-A3B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
More
Ornith 1.5 35B A3B on every GPU and Mac · Every model that runs on the RTX 5080 · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (ornith-ai/Ornith-1.5-35B-A3B), NVIDIA specs. Data as of 2026-11-17.