Radeon AI Pro R9700 x3 vs Tesla V100 x2
Best verified output tok/s per model (single-stream generation). Hover a value for the quant.
Radeon AI Pro R9700 x37 verified runs · best 58.8 tok/s
Tesla V100 x25 verified runs · best 96.1 tok/s
| Model | Radeon AI Pro R9700 x3 | Tesla V100 x2 |
|---|
| Qwen3.8-Flash-Next | 28.1 UD-IQ3_XXS | 96.1 IQ3XXS |
| Ornith-1.5-35B-A3B | 35.4 BF16 | 65.0 Q4_K_M |
| Qwen3-VL-8B-Instruct | 58.8 Q8_0 | — |
| Muse-Glimmer-30B | 47.8 UD-Q8_K_XL | — |
| Ling-3.0-flash | 39.3 Q4_0_ROCMFP4_STRIX_LEAN | — |
| Ornith-1.0-9B | 31.2 BF16 | — |
| Qwen3.8-27B | — | 24.0 Q8_K_XL |
| gemma-4-31B-it | 23.9 Q8_0 | — |
Head-to-head (models tested on both): Radeon AI Pro R9700 x3 0 · Tesla V100 x2 2 · tied 0 · data as of Sep 23, 2026. Full rules: methodology.
Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board