RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Ornith 1.5 35B A3B run on the 2x RTX 3090?

Yes. At 8K context the best fit is Q8_0, using about 36.2 GB of the 45.6 GB usable on the 2x RTX 3090. Estimated speed ceiling: ~297 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •13.1 GB Fits13.2 GB Fits13.7 GB Fits15.6 GB Fits857
3-bit (Q3_K_M) •16.5 GB Fits16.6 GB Fits17.0 GB Fits18.9 GB Fits672
4-bit (Q4_K_M) •21.3 GB Fits21.4 GB Fits21.9 GB Fits23.7 GB Fits513
5-bit (Q5_K_M) •24.7 GB Fits24.8 GB Fits25.2 GB Fits27.1 GB Fits440
6-bit (Q6_K) •29.4 GB Fits29.5 GB Fits29.9 GB Fits31.8 GB Fits367
8-bit (Q8_0) •36.2 GB Fits36.2 GB Fits36.7 GB Fits38.6 GB Fits297
16-bit (F16/BF16) •67.1 GB No67.2 GB No67.7 GB No69.6 GB No—

• real GGUF file size from bartowski/Ornith-1.5-35B-A3B-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.

More

Ornith 1.5 35B A3B on every GPU and Mac · Every model that runs on the 2x RTX 3090 · 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.