RTX 5070 vs RX 7900 XTX

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.

RTX 50705 sourced runs · best 185.8 tok/s

RX 7900 XTX6 verified runs · best 550.2 tok/s

Specs and evidence

	RTX 5070	RX 7900 XTX
VRAM	12 GB	24 GB
Sourced runs on the board	5	6
Models measured	5	5
Best output tok/s	185.8 tok/s	550.2 tok/s
Highest measured peak VRAM	9.0 GB	22.9 GB
Street price (latest snapshot)	—	—

Sourced rows only. Peak VRAM is recorded by the person who ran the benchmark, so it is a floor for what the card can hold, not a specification. Price snapshots.

Head-to-head

Only one model has been measured on both cards (Qwen3.8-27B). On that single data point RTX 5070 records 48.3 tok/s and RX 7900 XTX records 154.2 tok/s — treat it as one data point, not a ranking.

The measured matrix

Model	RTX 5070	RX 7900 XTX
Qwen3.5-0.8B	—	550.2 MQ4
LFM2.5-350M	—	398.4 MQ4
NVIDIA-Nemotron-3-Nano-4B	185.8 Q4_K_M	—
Apodex-1.1-mini	182.3 IQ1_M	—
Qwen3.8-27B	48.3 UD-Q2_K_XL	154.2 MQ4
Qwen3.6-35B-A3B	—	150.0 MQ4R
Ornith-1.5-9B	102.0 Q4_K_M	—
Qwen3.6-35B-A3B-abliterated-v4	—	82.1 Q8_0
Qwen3.8-Flash-Next	81.8 Q2_0	—

Head-to-head (models tested on both): RTX 5070 0 · RX 7900 XTX 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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