Alveo V80 vs Radeon AI Pro R9700

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.

Alveo V800 sourced runs · best — tok/s

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

Specs and evidence

	Alveo V80	Radeon AI Pro R9700
VRAM	32 GB	32 GB
Sourced runs on the board	0	14
Models measured	0	14
Best output tok/s	—	969.4 tok/s
Highest measured peak VRAM	—	92.2 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.

The measured matrix

Model	Alveo V80	Radeon AI Pro R9700
Qwen3.6-35B-A3B	—	969.4 MQ4R
Qwen3.5-0.8B	—	554.5 MQ4
LFM2.5-230M	—	520.0 MQ4
LFM2.5-350M	—	466.0 MQ4
Qwen3.5-27B	—	286.6 MQ4-AWQ
LFM2.5-8B-A1B	—	241.1 MQ4
gemma-4-E2B-it	—	169.7 Q8_0
gemma-4-E4B-it	—	137.0 Q4_K_M
Muse-Glimmer-30B	—	134.6 Dynamic-Q4_K_XL + DFlash2-Q4_K_M
Qwen3.8-27B	—	64.3 Q4_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

14 rows · 0 models on Alveo V80, 14 on Radeon AI Pro R9700 — no verified overlap yet, each side shows its own bests · data as of Oct 17, 2026. Full rules: methodology.

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