Radeon AI Pro R9700 x3 vs Tesla V100 PCIe 16GB

GPU AGPU B

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 R9700 x39 sourced runs · best 223.4 tok/s

Tesla V100 PCIe 16GB1 verified run · best 40.7 tok/s

Model	Radeon AI Pro R9700 x3	Tesla V100 PCIe 16GB
gpt-oss-120b	223.4 MXFP4	—
Nemotron-Cascade-2-30B-A3B	95.4 Q8_0	—
Qwen3-VL-8B-Instruct	58.8 Q8_0	—
Muse-Glimmer-30B	47.8 UD-Q8_K_XL	—
Qwen3.8-Flash-Next	28.1 UD-IQ3_XXS	40.7 Q2_0
Ling-3.0-flash	39.3 Q4_0_ROCMFP4_STRIX_LEAN	—
Ornith-1.5-35B-A3B	35.4 BF16	—
Ornith-1.0-9B	31.2 BF16	—
gemma-4-31B-it	23.9 Q8_0	—

Head-to-head (models tested on both): Radeon AI Pro R9700 x3 0 · Tesla V100 PCIe 16GB 1 · tied 0 · data as of Oct 11, 2026. Full rules: methodology.

Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board