Radeon AI Pro R9700 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.

Radeon AI Pro R970014 sourced runs · best 969.4 tok/s

RX 7900 XTX6 verified runs · best 550.2 tok/s

Specs and evidence

	Radeon AI Pro R9700	RX 7900 XTX
VRAM	32 GB	24 GB
Sourced runs on the board	14	6
Models measured	14	5
Best output tok/s	969.4 tok/s	550.2 tok/s
Highest measured peak VRAM	92.2 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

On the 4 models measured on both cards, Radeon AI Pro R9700 leads on 3, RX 7900 XTX on 1. The widest gap is on Qwen3.6-35B-A3B: Radeon AI Pro R9700 969.4 tok/s vs RX 7900 XTX 150.0 tok/s (Radeon AI Pro R9700 546% faster).

The measured matrix

Model	Radeon AI Pro R9700	RX 7900 XTX
Qwen3.6-35B-A3B	969.4 MQ4R	150.0 MQ4R
Qwen3.5-0.8B	554.5 MQ4	550.2 MQ4
LFM2.5-230M	520.0 MQ4	—
LFM2.5-350M	466.0 MQ4	398.4 MQ4
Qwen3.5-27B	286.6 MQ4-AWQ	—
LFM2.5-8B-A1B	241.1 MQ4	—
gemma-4-E2B-it	169.7 Q8_0	—
Qwen3.8-27B	64.3 Q4_0	154.2 MQ4
gemma-4-E4B-it	137.0 Q4_K_M	—
Muse-Glimmer-30B	134.6 Dynamic-Q4_K_XL + DFlash2-Q4_K_M	—
Qwen3.6-35B-A3B-abliterated-v4	—	82.1 Q8_0
DeepSeek-V4-Flash-0731	59.4 IQ2_XXS	—
Qwen 3.8 Flash-Next Base	57.0 IQ3_S	—
Qwen3.8-Flash-Next	25.6 IQ4_XS	—
GLM-5.3-Flash	17.4 UD-IQ1_M	—

Head-to-head (models tested on both): Radeon AI Pro R9700 3 · 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