RTX 3090 vs RTX PRO 6000 Blackwell x4

GPU AGPU B

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 309018 sourced runs · best 709.5 tok/s

RTX PRO 6000 Blackwell x49 verified runs · best 231.6 tok/s

Model	RTX 3090	RTX PRO 6000 Blackwell x4
LFM2.5-1.2B-Instruct	709.5 Q4_K_M	—
Qwen3.5-0.8B-MTP	476.1 Q6_K_XL	—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	353.7 NVFP4	—
LFM2.5-2.6B	305.6 Q4_K_M	—
Qwen3.5-4B-MTP	240.4 Q6_K_XL	—
DeepSeek-V4.1-Flash	26.0 EXL3 3.0 bpw	231.6 FP4+FP8 native
Qwen3.8-27B	164.6 EXL3-3.5bpw	—
Qwen3.5-9B-MTP	164.3 Q6_K_XL	—
Qwen3.8-Flash-Next	38.6 EXL3 2.50bpw	—
Ornstein3.6-27B-MTP-NSC-ACE-SABER	32.9 Q4_K_M	—
GLM-5.3-Flash	28.1 EXL3 3.05 bpw	—

Head-to-head (models tested on both): RTX 3090 0 · RTX PRO 6000 Blackwell x4 1 · tied 0 · data as of Oct 6, 2026. Full rules: methodology.

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