RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Ornith 1.5 122B run on the H200?

Yes. At 8K context the best fit is Q6_K, using about 96.6 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~459 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)44.7 GB Fits44.7 GB Fits45.3 GB Fits47.6 GB Fits1004
3-bit (Q3_K_M)57.9 GB Fits58.0 GB Fits58.6 GB Fits60.8 GB Fits770
4-bit (Q4_K_M)72.2 GB Fits72.3 GB Fits72.8 GB Fits75.1 GB Fits616
5-bit (Q5_K_M)84.0 GB Fits84.1 GB Fits84.6 GB Fits86.9 GB Fits529
6-bit (Q6_K)96.5 GB Fits96.6 GB Fits97.2 GB Fits99.4 GB Fits459
8-bit (Q8_0) •124 GB Tight125 GB Tight125 GB Tight127 GB Tight355
16-bit (F16/BF16) •233 GB No233 GB No234 GB No236 GB No—

• real GGUF file size from unsloth/Ornith-1.5-122B-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

Ornith 1.5 122B on every GPU and Mac · Every model that runs on the H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (ornith-ai/Ornith-1.5-122B), NVIDIA specs. Data as of 2026-11-17.