RTX PRO 6000 Blackwell x2

Nvidia · 192 GB VRAM

6recorded runs

204.5best tok/s

3sourced

Evidence: 3 sourced runs · 3 awaiting review · 1 independent source · first recorded Aug 30, 2026 · last recorded Sep 4, 2026. What these labels mean.

What fits on 192 GB — measured

Model	Quant	Peak VRAM	Headroom
GLM-5.3-Flash	EXL3-3.0bpw	186.6 GB	5.4 GB
DeepSeek-V4-Flash-Vision-Exp	FP8	183.1 GB	8.9 GB

Peak process memory recorded by the submitter on this card — evidence of what fit, not a guarantee. Plan with the VRAM calculator.

All benchmarks Compare RTX PRO 6000 Blackwell x2 →

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
RTX PRO 6000 Blackwell x2 · 192 GB	DeepSeek-V4-Flash-Vision-Exp	FP8	vllm 0.28.1rc1.dev137+g5ab628dd1	1048576	179.5 ✓	15057.6	183.1	src
RTX PRO 6000 Blackwell x2 · 192 GB	GLM-5.3-Flash	EXL3-3.0bpw	vllm 0.1.dev20111+g7f1e92bec.d20260827	700000	159.3 ✓	2396.3	186.6	src
RTX PRO 6000 Blackwell x2 · 192 GB	GLM-5.3-Flash	exl3	vllm 0.1.dev20111+g7f1e92bec.d20260827	131072	128.6 ✓	371.3	—	src
RTX PRO 6000 Blackwell x2 · 192 GB	Qwen3.8-Flash-Next	FP8_E4M3	vllm —	262144	204.5 …	—	—	src
RTX PRO 6000 Blackwell x2 · 192 GB	DeepSeek-V4-Flash-0731	FP8	vllm —	2048	185.6 …	491.3	—	src
RTX PRO 6000 Blackwell x2 · 192 GB	Qwen3.8-Flash-Next	NVFP4	vllm —	262144	93.5 …	437.7	—	src

Related reading: GPU buying guide · used GPUs · Value index · Street prices