Home › GPUs & Macs › NVIDIA RTX PRO 6000 Blackwell vs NVIDIA RTX PRO 6000 Blackwell Max-Q

NVIDIA RTX PRO 6000 Blackwell vs NVIDIA RTX PRO 6000 Blackwell Max-Q for local LLMs

Across 5 tests measured on both, the NVIDIA RTX PRO 6000 Blackwell is faster in 5 and generates a median 1.80× the tokens/s of the NVIDIA RTX PRO 6000 Blackwell Max-Q.

On gpt-oss 120B (MXFP4, llama-bench) the NVIDIA RTX PRO 6000 Blackwell generates 196 tokens/s and the NVIDIA RTX PRO 6000 Blackwell Max-Q 184 tokens/s (measured).

Same model, same quant, same test

ModelQuant / testRTX PRO 6000 Blackwell
tok/s
RTX PRO 6000 Blackwell Max-Q
tok/s
FasterSources and run details
gpt-oss 120BMXFP4
llama-bench
196
CUDA
184
CUDA
RTX PRO 6000 Blackwell +7%llama.cpp #15396 RTX PRO 6000 Blackwell · llama.cpp #15396 RTX PRO 6000 Blackwell Max-Q
gpt-oss 20BMXFP4
llama-bench
287
CUDA
250
CUDA
RTX PRO 6000 Blackwell +15%llama.cpp #15396 RTX PRO 6000 Blackwell · llama.cpp #15396 RTX PRO 6000 Blackwell Max-Q
Llama 3.1 8B InstructQ4_K_M
LocalScore
85.8
llamafile
46.2
llamafile
RTX PRO 6000 Blackwell +86%LocalScore RTX PRO 6000 Blackwell · LocalScore RTX PRO 6000 Blackwell Max-Q
Llama 3.2 1B InstructQ4_K_M
LocalScore
191
llamafile
106
llamafile
RTX PRO 6000 Blackwell +80%LocalScore RTX PRO 6000 Blackwell · LocalScore RTX PRO 6000 Blackwell Max-Q
Qwen2.5 14B InstructQ4_K_M
LocalScore
64.0
llamafile
23.7
llamafile
RTX PRO 6000 Blackwell +170%LocalScore RTX PRO 6000 Blackwell · LocalScore RTX PRO 6000 Blackwell Max-Q

Generation speed in tokens/s, best measured backend for each chip (shown under the number). Backends can differ between the two chips; check them before drawing conclusions. Measured results only, nothing estimated.

Specs

NVIDIA RTX PRO 6000 BlackwellNVIDIA RTX PRO 6000 Blackwell Max-Q
Memory96 GB96 GB
Memory bandwidth1792 GB/s1792 GB/s

All results for the NVIDIA RTX PRO 6000 Blackwell · All results for the NVIDIA RTX PRO 6000 Blackwell Max-Q · More comparisons