| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Ornith 1.5 397BModel source: derived262,144 tokens max native context | 397Bactive 17B | 238.2 GB4-bit quantization |
| Compatible hardware Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone. | ||||
|---|---|---|---|---|
| Hardware | Memory | Bandwidth | vLLM | Estimated generation |
| M5 Ultra | 256 GBUnified RAM | 1200 GB/s | no | 46 tok/s4-bit quantization |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 152 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 203 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 203 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 220 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 220 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 220 tok/s4-bit quantization |
Evaluates Ornith-1.5-397B-MLX-Q9 performance using Inferencer App on M3 Ultra 512 GiB against claims of surpassing GLM 5.2, Opus and Qwen 3.8 MAX.