Radeon AI Pro R9700 vs Tesla V100 x2
Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
Radeon AI Pro R970014 sourced runs · best 969.4 tok/s
Tesla V100 x25 verified runs · best 96.1 tok/s
Specs and evidence
| Radeon AI Pro R9700 | Tesla V100 x2 | |
|---|---|---|
| VRAM | 32 GB | 32 GB |
| Sourced runs on the board | 14 | 5 |
| Models measured | 14 | 3 |
| Best output tok/s | 969.4 tok/s | 96.1 tok/s |
| Highest measured peak VRAM | 92.2 GB | 25.2 GB |
| Street price (latest snapshot) | — | — |
Head-to-head
On the 2 models measured on both cards, Radeon AI Pro R9700 leads on 1, Tesla V100 x2 on 1. The widest gap is on Qwen3.8-Flash-Next: Radeon AI Pro R9700 25.6 tok/s vs Tesla V100 x2 96.1 tok/s (Tesla V100 x2 275% faster).
The measured matrix
| Model | Radeon AI Pro R9700 | Tesla V100 x2 |
|---|---|---|
| Qwen3.6-35B-A3B | 969.4 | — |
| Qwen3.5-0.8B | 554.5 | — |
| LFM2.5-230M | 520.0 | — |
| LFM2.5-350M | 466.0 | — |
| Qwen3.5-27B | 286.6 | — |
| LFM2.5-8B-A1B | 241.1 | — |
| gemma-4-E2B-it | 169.7 | — |
| gemma-4-E4B-it | 137.0 | — |
| Muse-Glimmer-30B | 134.6 | — |
| Qwen3.8-Flash-Next | 25.6 | 96.1 |
| Ornith-1.5-35B-A3B | — | 65.0 |
| Qwen3.8-27B | 64.3 | 24.0 |
| DeepSeek-V4-Flash-0731 | 59.4 | — |
| Qwen 3.8 Flash-Next Base | 57.0 | — |
| GLM-5.3-Flash | 17.4 | — |