Radeon AI Pro R9700 x2 vs RTX 3080

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 x23 sourced runs · best 131.4 tok/s

RTX 30809 verified runs · best 277.8 tok/s

Specs and evidence

	Radeon AI Pro R9700 x2	RTX 3080
VRAM	32 GB	10 GB
Sourced runs on the board	3	9
Models measured	3	9
Best output tok/s	131.4 tok/s	277.8 tok/s
Highest measured peak VRAM	44.6 GB	9.7 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 2 models measured on both cards, Radeon AI Pro R9700 x2 leads on 0, RTX 3080 on 2. The widest gap is on Qwen3.8-27B-Uncensored: Radeon AI Pro R9700 x2 51.8 tok/s vs RTX 3080 74.1 tok/s (RTX 3080 43% faster).

The measured matrix

Model	Radeon AI Pro R9700 x2	RTX 3080
LFM2.5-8B-A1B	—	277.8 Q6_K
gemma-4-26B-A4B-it	131.4 Q8_K_XL	—
Ornith-1.5-9B	—	82.8 Q6_K
Qwen3.8-27B-Uncensored	51.8 Q8_0	74.1 IQ2_XXS
Bonsai-27B	—	72.9 Q1_0
gemma-4-12B-it-qat	—	71.2 Q4_0
Ornith-1.5-35B-A3B	—	64.4 Q4_K_M
gpt-oss-20b	—	57.1 MXFP4
Qwen3.8-27B	43.6 Q8_K_XL	44.4 IQ2_XXS
Muse-Glimmer-30B	—	6.0 Q4_K_M

Head-to-head (models tested on both): Radeon AI Pro R9700 x2 0 · RTX 3080 2 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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