NVIDIA · Blackwell

Best AI Models for NVIDIA RTX PRO 5000 Blackwell (72 GB)

Runs 70B models well; 120B MoE only just fits.

72 GB GDDR71344 GB/s260 TFLOPS FP16300 WBlackwell 2025

What LLMs can the RTX PRO 5000 Blackwell run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 42.8 t/s	42.8 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 209 t/s	209 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 222 t/s	222 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 42.8 t/s	42.8 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 181 t/s	181 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 209 t/s	209 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 222 t/s	222 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 42.8 t/s	42.8 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 209 t/s	209 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 222 t/s	222 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Math Score	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 181 t/s	181 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 42.8 t/s	42.8 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 222 t/s	222 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 268 t/s	268 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 233 t/s	233 tok/s	Q4_K_M · 13.1 GB
3	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 222 t/s	222 tok/s	Q4_K_M · 19.3 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 209 t/s	209 tok/s	Q4_K_M · 16.5 GB
5	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 200 t/s	200 tok/s	Q4_K_M · 19.4 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 50.1 t/s	50.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 42.8 t/s	42.8 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 209 t/s	209 tok/s	Q4_K_M · 16.5 GB
5	MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 200 t/s	200 tok/s	Q4_K_M · 22.1 GB

See all 379 models on the RTX PRO 5000 Blackwell →Best quant that fits · speeds estimated on this card

About the RTX PRO 5000 Blackwell

The RTX PRO 5000 Blackwell runs 70B models well. Blackwell generation, released 2025.

GenerationBlackwellreleased 2025

RTX PRO 5000 Blackwell strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 168 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 20.7 GB free
Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 1.9 s
FP8 and NVFP4 run natively: Blackwell takes FP8 and NVFP4 checkpoints in vLLM as published

RTX PRO 5000 Blackwell tokens per second by model size

Output speed depends on memory bandwidth (1344 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
137tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
92.0tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
50.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
181tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
18.8tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB tight · Q4_K_M
168tok/s

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1253 models on the RTX PRO 5000 Blackwell

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA RTX PRO 5000 Blackwell — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
K2 Horizon 7B Uno7BChat Q4_K_M·189.1 t/s	Q4_K_M	7.1 GB10%	189.1 t/s	—	S99, Runs great
K2 Horizon 7B9.0BChatFunctions Q4_K_M·145.6 t/s	Q4_K_M	8.1 GB11%	145.6 t/s	524K	S97, Runs great
Molmo2 4B4.9BVision Q4_K_M·256.9 t/s	Q4_K_M	4.7 GB7%	256.9 t/s	37K	S100, Runs great
Qwen3 4B Mamba3 Hybrid Stage2b Kd Bias04.7BChatFunctions Q4_K_M·262.3 t/s	Q4_K_M	4.7 GB6%	262.3 t/s	41K	S100, Runs great
Beetle Monolingual Fineweb3 Eng194MChat BF16·2031.6 t/s	BF16	0.4 GB1%	2031.6 t/s	1K	S100, Runs great
Tiny Lfm2ForCausalLM 2.5526340ChatFunctions Q4_K_M·2912.0 t/s	Q4_K_M	0.5 GB1%	2912.0 t/s	128K	S100, Runs great
Sarvam 30B32.2BChatFunctions Q4_K_M·237.9 t/s	Q4_K_M	19.9 GB28%	237.9 t/s	131K	S100, Runs great
DiffuRefill 1B1BChat BF16·336.0 t/s	BF16	2.6 GB4%	336.0 t/s	2K	S100, Runs great
Qwen3.5 0.8B873MVisionFunctions Q4_K_M·1004.1 t/s	Q4_K_M	0.9 GB1%	1004.1 t/s	262K	S100, Runs great
Tiny NemotronHForCausalLM 3.5 Lightning4MChatFunctions Q4_K_M·87360.0 t/s	Q4_K_M	0.3 GB0%	87360.0 t/s	262K	S100, Runs great
Z Image Turbo6.2BChat BF16·64.5 t/s	BF16	15.9 GB22%	64.5 t/s	—	A84, Runs well
Tiny Lfm2ForCausalLM525956ChatFunctions Q4_K_M·2912.0 t/s	Q4_K_M	0.5 GB1%	2912.0 t/s	128K	S100, Runs great
Qwen3 VL 8B Instruct8.8BVisionFunctions Q4_K_M·149.1 t/s	Q4_K_M	8.0 GB11%	149.1 t/s	262K	S97, Runs great
OTel LLM E4B IT4BChatFunctions Q4_K_M·299.2 t/s	Q4_K_M	3.2 GB4%	299.2 t/s	131K	S100, Runs great
Tiny Phi3ForCausalLM 3514984Chat Q4_K_M·2912.0 t/s	Q4_K_M	0.3 GB0%	2912.0 t/s	4K	S100, Runs great

RTX PRO 5000 Blackwell specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 72 GB GDDR7
Memory bandwidth: 1344.0 GB/s
FP16 (dense): 260.00 TFLOPS
CUDA cores: 14,080
Tensor cores: 440
Compute capability: 12.0
TDP: 300 W
Released: 2025-12-18
MSRP: $4,500

RTX PRO 5000 Blackwell FAQ

What is the largest model the RTX PRO 5000 Blackwell can run?

NVIDIA Nemotron 3 Super 120B A12B BF16 (123.6B) is the largest at 4-bit or better: at Q4_K_S it uses 70.0 GB of 72 GB, and runs at about 75.3 tok/s.

Can the RTX PRO 5000 Blackwell run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 72 GB, and it is the best model that runs well on this card.

How many tokens per second does the RTX PRO 5000 Blackwell give?

About 50.1 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 1.9 s on a 4K-token prompt.

What power supply does the RTX PRO 5000 Blackwell need?

Plan a 600 W PSU (2× the 300 W TDP).

Is 72 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 11 coding models that fit, runs at about 50 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 48 GB VRAM GPUs with 72 GB or more