RX 9070 XT 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.

Sourced data on this pair is thin — most of the board is still partial. Submit your own run and help fill the matrix: one prompt, three steps, no downloads.

RX 9070 XT3 sourced runs · best 545.3 tok/s

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

Model	RX 9070 XT	Tesla V100 PCIe 16GB
Qwen3.5-0.8B	545.3 MQ4	—
LFM2.5-230M	481.8 MQ4	—
LFM2.5-350M	437.7 MQ4	—
Qwen3.8-Flash-Next	—	40.7 Q2_0

4 rows · 3 models on RX 9070 XT, 1 on Tesla V100 PCIe 16GB — no verified overlap yet, each side shows its own bests · data as of Oct 11, 2026. Full rules: methodology.

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