Back to all offerings

NVIDIA RTX PRO 4000

24 GB VRAM2 providers8 offerings6 regions

The NVIDIA RTX PRO 4000 is an enterprise-class GPU built on the Blackwell architecture, featuring 24 GB of memory. Currently available from 2 providers starting at $0.23/GPU/hour, with a market median of $0.30/GPU/hour across 8 configurations.

Cheapest
$0.230/hr
Vast.ai
Median
$0.295/hr
across 8 offerings
Most expensive
$0.570/hr
Runpod
90-day trend
+55.3%
median rate

Hardware specifications

Same across all providers

Architecture
Blackwell
Brand
NVIDIA
Series
RTX PRO
Market price history

Median price across all providers

Prices updated 2 hours ago

2 offerings from 2 providers

Sorted by price ascending. Compare configurations side-by-side.

ProviderCountvCPURAMRegionPer GPU hourTotal/hrAction
Runpod logoRunpodPromoted
Up to$500creditAffiliate promotion — we may earn a commission.
×11231 GB
Romania
$0.570$0.57Launch
Vast.ai logoVast.aiReferral linkTrendingCheapest
×22063 GB
FranceUnited StatesAustria+2
From$0.230
+12.5% 30d
From$0.46
Launch
Runpod logoRunpodReferral linkTrending
Up to$500credit
×11231 GB
Romania
$0.570
$0.57
Launch

LLMs that fit on the NVIDIA RTX PRO 4000

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 24 GB per GPU. Showing the 12 largest that fit.

ModelParameters16-bit8-bit4-bit
Qwen3.6 35B-A3B
Alibaba
35B
3B active
86 GB
Too large
47 GB
Barely fits on 2×
28 GB
2× · 20 GB free
or 1× · 4% spare
Qwen3 32B
Alibaba
32.8B
79 GB
Too large
43 GB
2× · 4.8 GB free
25 GB
2× · 23 GB free
or 1× · 14% spare
Gemma 4 31B
Google
31.3B
75 GB
Too large
41 GB
2× · 6.7 GB free
24 GB
2× · 24 GB free
or 1× · 19% spare
GLM-4.7 Flash
Z.ai
31.2B
75 GB
Too large
41 GB
2× · 6.8 GB free
24 GB
Barely fits on 1×
Qwen3.6 27B
Alibaba
27.8B
67 GB
Too large
37 GB
2× · 11 GB free
21 GB
1× · 2.7 GB free
Mistral Small 3.2 24B
Mistral AI
24B
58 GB
Too large
32 GB
2× · 16 GB free
18 GB
1× · 5.6 GB free
gpt-oss-20b
OpenAI
21B
3.6B active
Not released
Not released
17 GB
1× · 7.5 GB free
Gemma 3 12B
Google
12.2B
29 GB
2× · 19 GB free
16 GB
1× · 7.9 GB free
9.4 GB
1× · 15 GB free
Granite 4.1 8B
IBM
8.8B
21 GB
1× · 2.9 GB free
12 GB
1× · 12 GB free
6.8 GB
1× · 17 GB free
Qwen3 8B
Alibaba
8.2B
20 GB
1× · 4.3 GB free
11 GB
1× · 13 GB free
6.3 GB
1× · 18 GB free
Llama 3.1 8B Instruct
Meta
8B
19 GB
1× · 4.7 GB free
11 GB
1× · 13 GB free
6.2 GB
1× · 18 GB free
Mistral 7B Instruct v0.3
Mistral AI
7.2B
17 GB
1× · 6.6 GB free
9.6 GB
1× · 14 GB free
5.6 GB
1× · 18 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this

Want more from this page?

See incorrect data?

Frequently asked questions

How much does the RTX PRO 4000 cost per hour?
The RTX PRO 4000 starts at $0.23 per GPU-hour, with a median of $0.30 across 8 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the RTX PRO 4000?
2 providers currently list the RTX PRO 4000: Runpod, Vast.ai. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the RTX PRO 4000 have?
The RTX PRO 4000 comes with 24 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Which LLMs can I run on the RTX PRO 4000?
With 24 GB of VRAM, a single RTX PRO 4000 can serve models such as GLM-4.7 Flash, Qwen3.6 27B, Mistral Small 3.2 24B, gpt-oss-20b. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.
What's the biggest LLM I can run on multiple RTX PRO 4000 GPUs?
The largest models we track that fit across several RTX PRO 4000 cards are Qwen3.6 35B-A3B on 2 GPUs at 8-bit, Qwen3 32B on 2 GPUs at 8-bit, Gemma 4 31B on 2 GPUs at 8-bit. A multi-GPU configuration means you rent and pay for every card for the whole run, and splitting a model across cards costs throughput as well: the GPUs exchange activations on every token, so performance depends on how fast they are wired together. We do not track interconnect, so check the provider's node specification. The table above gives the smallest configuration for each model at 16-bit, 8-bit and 4-bit precision.
Where is the RTX PRO 4000 cheapest?
The lowest on-demand price we currently track for the RTX PRO 4000 is $0.23 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.