DiggTop
Menu
⌕

Radeon AI Pro R9700 vs RTX PRO 6000 Blackwell

Pick a different pair →

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
RTX PRO 6000 Blackwell29 verified runs · best 1271.3 tok/s

Specs and evidence

Radeon AI Pro R9700RTX PRO 6000 Blackwell
VRAM32 GB96 GB
Sourced runs on the board1429
Models measured1423
Best output tok/s969.4 tok/s1271.3 tok/s
Highest measured peak VRAM92.2 GB72.7 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 3 models measured on both cards, Radeon AI Pro R9700 leads on 1, RTX PRO 6000 Blackwell on 2. The widest gap is on Qwen3.8-27B: Radeon AI Pro R9700 64.3 tok/s vs RTX PRO 6000 Blackwell 296.0 tok/s (RTX PRO 6000 Blackwell 360% faster).

The measured matrix

ModelRadeon AI Pro R9700RTX PRO 6000 Blackwell
MobileLLM-125M—1271.3 Q8_0
Qwen2.5-0.5B-Instruct—1060.0 Q8_0
MobileLLM-350M—980.8 Q8_0
Qwen3.6-35B-A3B969.4 MQ4R330.2 NVFP4
SmolLM2-360M-Instruct—968.1 Q8_0
Qwen3-0.6B—956.4 Q4_K_M
Llama-3.2-1B-Instruct—699.9 Q8_0
gemma-3-1b-it—664.3 Q4_K_M
Qwen3.5-0.8B554.5 MQ4—
LFM2.5-230M520.0 MQ4—
Llama-3.2-3B-Instruct—489.2 Q4_K_M
LFM2.5-350M466.0 MQ4—
Ling-3.0-tiny—369.1 Q4_K_M
Ornith-1.0-35B—309.7 Q4_K_M
Qwen3.8-27B64.3 Q4_0296.0 NVFP4
Qwen3.5-27B286.6 MQ4-AWQ—
LFM2.5-8B-A1B241.1 MQ4—
DeepSeek-Coder-V2-Lite-Instruct—237.3 FP8
Qwen3-Coder-Next—174.3 FP8
gemma-4-E2B-it169.7 Q8_0—
Llama-3.1-8B-Instruct—158.1 FP8
Muse-Glimmer-30B134.6 Dynamic-Q4_K_XL + DFlash2-Q4_K_M152.2 NVFP4
gemma-4-E4B-it137.0 Q4_K_M—
Qwen3.8-27B-MTP—112.1 NVFP4
Qwen3.6-27B—101.4 FP8
Qwen3-14B—90.8 FP8
Kimi-Linear-48B-A3B-Instruct—90.0 Q8_0
Qwen3.6-27B-MTP—60.1 Q6_K
DeepSeek-V4-Flash-073159.4 IQ2_XXS—
Qwen 3.8 Flash-Next Base57.0 IQ3_S—
Qwen2.5-Coder-14B-Instruct—50.3 BF16
Qwen3-Coder-30B-A3B-Instruct—26.1 FP8
Qwen3.8-Flash-Next25.6 IQ4_XS—
GLM-5.3-Flash17.4 UD-IQ1_M—

Head-to-head (models tested on both): Radeon AI Pro R9700 1 · RTX PRO 6000 Blackwell 2 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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

↑