NVIDIA · Blackwell · 24 GB VRAM tier

Best AI Models for NVIDIA RTX PRO 4000 Blackwell (24 GB)

Runs 27–31B and 35B MoE models well; 70B doesn't fit in 24 GB.

24 GB GDDR7672 GB/s147 TFLOPS FP16145 WBlackwell 2025

What LLMs can the RTX PRO 4000 Blackwell run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 21.4 t/s	21.4 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 162 t/s	162 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 21.4 t/s	21.4 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 113 t/s	113 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 162 t/s	162 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 21.4 t/s	21.4 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 162 t/s	162 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 · 25.1 t/s	25.1 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 113 t/s	113 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 21.4 t/s	21.4 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 162 t/s	162 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 138 t/s	138 tok/s	Q4_K_M · 13.1 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 176 t/s	176 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 138 t/s	138 tok/s	Q4_K_M · 13.1 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 162 t/s	162 tok/s	Q4_K_M · 19.3 GB
3	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 136 t/s	136 tok/s	Q4_K_M · 19.4 GB
4	Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB · 136 t/s	136 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 21.4 t/s	21.4 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 126 t/s	126 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 25.1 t/s	25.1 tok/s	Q4_K_M · 17.9 GB

See all 327 models on the RTX PRO 4000 Blackwell →Best quant that fits · speeds estimated on this card

About the RTX PRO 4000 Blackwell

The RTX PRO 4000 Blackwell runs 27–31B and 35B MoE models well. Blackwell generation, released 2025.

GenerationBlackwellreleased 2025

RTX PRO 4000 Blackwell strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 113 tok/s in 22 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 6.1 GB free
Low power draw: 145 W board power; a 300 W PSU is enough

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 24 GB here

RTX PRO 4000 Blackwell tokens per second by model size

Output speed depends on memory bandwidth (672 GB/s). Grey rows need more than 24 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
68.7tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
46.0tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
25.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
113tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

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

All 1141 models on the RTX PRO 4000 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 4000 Blackwell — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
GOT OCR2 0716MVision Q4_K_M·469.7 t/s	Q4_K_M	2.3 GB10%	469.7 t/s	33K	S100, Runs great
Natural Sql 7B6.9BChat Q4_K_M·80.1 t/s	Q4_K_M	6.5 GB27%	80.1 t/s	4K	S88, Runs great
Phi 4 Mini Flash Reasoning3.9BChatMathCodeReasoning Q4_K_M·148.1 t/s	Q4_K_M	5.3 GB22%	148.1 t/s	262K	S97, Runs great
Llama 68M68MChat Q4_K_M·10920.0 t/s	Q4_K_M	0.0 GB0%	10920.0 t/s	2K	S100, Runs great
Aya Expanse 8B8.0BChat BF16·24.7 t/s	BF16	20.2 GB84%	24.7 t/s	—	B60, Decent
Dummy GPT2 Correct Vocab2MChat Q4_K_M·43680.0 t/s	Q4_K_M	0.0 GB0%	43680.0 t/s	1K	S100, Runs great
Pythia 1B1.1BChat Q4_K_M·615.2 t/s	Q4_K_M	0.7 GB3%	615.2 t/s	2K	S100, Runs great
T5 Paraphrase Paws223MChat Q4_K_M·2912.0 t/s	Q4_K_M	0.1 GB1%	2912.0 t/s	1K	S100, Runs great
GLM 4.1V 9B Thinking10.3BVisionReasoning Q4_K_M·66.6 t/s	Q4_K_M	7.2 GB30%	66.6 t/s	66K	S85, Runs great
LFM2.5 1.2B Thinking1.2BChat Q4_K_M·408.2 t/s	Q4_K_M	1.2 GB5%	408.2 t/s	128K	S100, Runs great
Qwen3 4B Thinking 25074.0BChatFunctions Q4_K_M·150.6 t/s	Q4_K_M	4.2 GB18%	150.6 t/s	262K	S97, Runs great
Openai GPT120MChat Q4_K_M·5460.0 t/s	Q4_K_M	0.1 GB0%	5460.0 t/s	1K	S100, Runs great
Opt 1.3B1.3BChat FP16·152.7 t/s	FP16	2.9 GB12%	152.7 t/s	2K	S97, Runs great
DialoGPT Small176MChat Q4_K_M·3640.0 t/s	Q4_K_M	0.1 GB1%	3640.0 t/s	1K	S100, Runs great
Phi 1 51.4BChatCode Q4_K_M·464.7 t/s	Q4_K_M	0.9 GB4%	464.7 t/s	2K	S100, Runs great

Rent NVIDIA RTX PRO 4000 Blackwell in the cloud

Hourly rate on demand for one RTX PRO 4000 Blackwell.

Vast.aiMarketplaceLowest price
from$0.23/hr
Deploy
RunPod$5+ bonus credit
from$0.57/hr
Deploy

Buying one ($1,500) costs as much as ~6,600 hours of rental, about 27 months at 8 hours a day.

Cost per million tokens

Output-token cost on an RTX PRO 4000 Blackwell rented at $0.23/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.

Model	Quant	Speed	Per 1M output
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16	Q4_K_M	162 tok/s	$0.39$0.0045 input
Gemma 4 26B A4B IT	Q4_K_M	126 tok/s	$0.50$0.0084 input
GLM 4.7 Flash	Q4_K_M	108 tok/s	$0.59$0.0088 input
Qwen3.8 27B	Q4_K_M	25 tok/s	$2.52$0.053 input
Muse Glimmer 30B	Q4_K_M	24 tok/s	$2.66$0.057 input

RTX PRO 4000 Blackwell specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 24 GB GDDR7
Memory bandwidth: 672.0 GB/s
FP16 (dense): 147.25 TFLOPS
CUDA cores: 8,960
Tensor cores: 280
Compute capability: 12.0
TDP: 145 W
Released: 2025-04-01
MSRP: $1,500

RTX PRO 4000 Blackwell FAQ

What is the largest model the RTX PRO 4000 Blackwell can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB of 24 GB, and runs at about 113 tok/s.

Can the RTX PRO 4000 Blackwell run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 24 GB, and it is the best model that runs well on this card.

Can the RTX PRO 4000 Blackwell run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 24 GB on this card.

How many tokens per second does the RTX PRO 4000 Blackwell give?

About 25.1 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 3.4 s on a 4K-token prompt.

What power supply does the RTX PRO 4000 Blackwell need?

Plan a 300 W PSU (2× the 145 W TDP).

Is 24 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 9 coding models that fit, runs at about 25 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 24 GB or more RTX 5090 RTX 3090 Ti