What AI models can the NVIDIA RTX PRO 5000 Blackwell 72GB run?

VRAM: 72.0 GB
Usable for models: 72.0 GB
Memory bandwidth: 1,344 GB/s
FP16 compute: 65.0 TFLOPS
Released: 2025

Specifications

Maker	NVIDIA
Type	Workstation / datacenter graphics card
Video memory (VRAM)	72.0 GB
Usable for AI models	72.0 GB
Memory bandwidth	1,344 GB/s
FP16 compute	65.0 TFLOPS
Interface	PCIe 5.0
Released	2025

1 product with the NVIDIA RTX PRO 5000 Blackwell 72GB

NVIDIA RTX PRO 5000 BlackwellNVIDIA · Workstation card · 48 or 72 GBMaker’s page (opens in a new tab)

Best LLMs for the NVIDIA RTX PRO 5000 Blackwell 72GB

Grade · points	Model	Quant	Memory	Speed	Fit
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Gemma 4 26B-A4BGoogle	`F16`	56.2 GB	50.9 tok/s	Runs well
95 ptsExcellent (S) · 95 of 100 points: Model quality 42.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15	Qwen3.6 35B-A3BAlibaba	`Q8_0`	42.5 GB	140 tok/s	Runs well
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15	Qwen3.5 35B-A3BAlibaba	`Q8_0`	42.5 GB	140 tok/s	Runs well
94 ptsExcellent (S) · 94 of 100 points: Model quality 40.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15	Ornith 1.5 35B-A3BDeepReinforce	`Q8_0`	42.5 GB	140 tok/s	Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15	Apodex 1.1 Mini (35B-A3B)Apodex	`Q8_0`	42.5 GB	140 tok/s	Runs well
93 ptsExcellent (S) · 93 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15	Ornith 1.0 35B-A3BDeepReinforce	`Q8_0`	42.5 GB	140 tok/s	Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3 Coder Next (80B-A3B)Alibaba	`Q5_K_M`	61.0 GB	227 tok/s	Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.3/15	Agents-A1 35B-A3BInternScience	`Q8_0`	41.6 GB	140 tok/s	Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15	Qwen AgentWorld 35B-A3BAlibaba	`Q8_0`	41.1 GB	140 tok/s	Runs well
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	Qwen3-Next 80B-A3B ThinkingAlibaba	`Q6_K`	71.1 GB	191 tok/s	Tight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	gpt-oss 120BOpenAI	`MXFP4`	71.1 GB	173 tok/s	Tight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.1/15	GLM-4.7 Flash (30B-A3B)Zhipu AI	`Q8_0`	37.7 GB	140 tok/s	Runs well

Best Image models for the NVIDIA RTX PRO 5000 Blackwell 72GB

Grade · points	Model	Precision	Memory	Time per output	Fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.9/15	FLUX.2 [klein] 9BBlack Forest Labs	`FP16`	37.1 GB	2.2 s	Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 40.6/45, Memory fit 25.0/25, Speed 7.6/15, Memory use 15.0/15	FLUX.2 [dev]Black Forest Labs	`FP8`	59.7 GB	39 s	Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 36.9/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 11.7/15	FLUX.1 Krea [dev]Black Forest Labs	`FP16`	36.4 GB	14 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.0/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 11.7/15	FLUX.1 [dev]Black Forest Labs	`FP16`	36.4 GB	14 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 37.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15	Z-Image TurboAlibaba (Tongyi)	`FP16`	22.7 GB	3.0 s	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 10.8/15	HiDream-I1 FastHiDream.ai	`FP8`	33.7 GB	11 s	Runs well

Best Video models for the NVIDIA RTX PRO 5000 Blackwell 72GB

Grade · points	Model	Precision	Memory	Time per output	Fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 37.9/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 14.2/15	LTX-2.3Lightricks	`FP8`	44.3 GB	7.2 min	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	LTX-Video 13B 0.9.8 (distilled)Lightricks	`FP16`	47.9 GB	72 s	Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 14.2/15	LTX-2 (19B, video + audio)Lightricks	`FP8`	44.3 GB	7.2 min	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	Wan 2.2 I2V A14BAlibaba	`FP16`	58.0 GB	31.9 min	Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	Wan 2.2 T2V A14BAlibaba	`FP16`	58.0 GB	31.9 min	Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.