NVIDIA RTX PRO 6000 Blackwell 96GB 96GB GPU memory, body cost separate
1,792 GB/s 96GB ECC VRAM workstation GPU. Fully load 70B to 120B 4-bit models on a single card, all within the available 93GB VRAM budget.
Speed and memory for the same model
Hardware core specifications
- Available memory
- 93GB
- Memory bandwidth
- 1792GB/s
- Estimated sustained LLM load
- About 650W
- Korean price range (KRW)
- 2,550 × KRW 10,000–2,647 × KRW 10,000
Who it fits
- Utilizes 93GB of available memory
- CUDA-based local inference
- GLM-5.3-Flash (MoE) level high-speed generation
Skip it if
Prices cover the GPU alone; electricity estimates cover the entire PC including the GPU. Add the host PC, power supply and cooling to your purchase budget.
Recommended format for each device 4K input
The model you will experience with this equipment
K2 Horizon 0.9B
Required 1.03GB · spare time
llama.cpp CUDA · Q4_K_M
Decode
2637.3 ~ 2907.8 tok/s
First token
0.11 to 0.19 seconds
GLM-5.3-Flash (MoE)
recommendedRequired 190.21GB · tight
llama.cpp CUDA · Q4_K_M
Decode
6.6 ~ 6.6 tok/s
First token
3.7 to 6.0 seconds
Actual speed varies with runtime version, cooling, context length and quantization file.
On sales pages, look at memory before chips.
The model and speed assumptions above change if the product is not the 96GB configuration.
Frequently asked questions
- Which local LLM can be run on RTX PRO 6000 96GB?
- K2 Horizon 0.9B, GLM-5.3-Flash (MoE) and others with a 4K input and the recommended format. Required memory varies by model and context length.
- How much power does a local LLM on an RTX PRO 6000 96GB consume?
- Sustained load is about 650 W, with an actual range of 520–780 W.
- Are the displayed token speeds ground truth?
- This is a range aligned to collected benchmark measurements under the same conditions. Combinations without a matching measurement are estimated from the nearest result and vary with runtime, cooling, quantization file and context length.
Equipment to compare together
similar memory
Studio M4 Max 128GB
Suits people who want to compare a wide range from 70B-class to high-precision models in a single finished machine.
similar memory
Ryzen AI Max+ 395 128GB
It is attractive when you have large amounts of integrated memory at a low price and can handle runtime settings directly.
similar memory
DGX Spark 128GB
This is for handling a large model on one machine without splitting it across several graphics cards. You should have a reason to buy 128GB. If the model you need now fits in 24GB or 32GB, do not assume Spark will be faster just because it has more memory.