| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Qwen 3.5 122BModel source: provider262,144 tokens max native context | 122Bactive 10B | 73.2 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 |
| Radeon 8060S 96GB | 96 GBUnified RAM | 256 GB/s | yes | 17 tok/s4-bit quantization |
| DGX Spark | 128 GBUnified RAM | 273 GB/s | yes | 18 tok/s4-bit quantization |
| M5 Max | 128 GBUnified RAM | 614 GB/s | no | 40 tok/s4-bit quantization |
| M3 Ultra | 96 GBUnified RAM | 819 GB/s | no | 52 tok/s4-bit quantization |
| M5 Ultra | 256 GBUnified RAM | 1200 GB/s | no | 74 tok/s4-bit quantization |
| RTX PRO 6000 | 96 GBGPU VRAM | 1792 GB/s | yes | 105 tok/s4-bit quantization |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 223 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 284 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 284 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 304 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 304 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 304 tok/s4-bit quantization |
Tests combining multiple GPUs into a single desktop setup with 224GB of memory to evaluate performance beyond intended specifications using Strix Halo, LLM and Nvidia components.