Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run Qwen2.5 72B?

RTX PRO 6000 Blackwell × Qwen2.5 72B8K context
YesRuns fully on the GPU
Memory at Q8_080.5 GB of 96 GB
Weights 77.2 GBKV cache 2.7 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Speed~14tokens per second
Max context32Kthe model's full window
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX PRO 6000 Blackwell can run Qwen2.5 72B fully in VRAM at Q8_0 (near-lossless), using about 80.5 GB of the 96 GB available, at roughly 14 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen2.5 72B:

ollama run qwen2.5:72b

Ollama's default download is Q4_K_M (about 47.4 GB here). You have room for Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX PRO 6000 Blackwell

Run it in the cloud

No NVIDIA RTX PRO 6000 Blackwell? Run Qwen2.5 72B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 96 GB the NVIDIA RTX PRO 6000 Blackwell can use.

QuantQualityMemoryFits?Speed
FP16Full quality148.7 GBToo big—
Q8_0Near-lossless80.5 GBFits~14 tok/s
Q6_KExcellent62.9 GBFits~18 tok/s
Q5_K_MVery good55 GBFits~21 tok/s
Q4_K_MGood, most popular47.4 GBFits~24 tok/s
Q3_K_MNoticeably degraded38.8 GBFits~30 tok/s
Q2_KHeavily degraded30.5 GBFits~39 tok/s

Measured speed from real RTX PRO 6000 Blackwell owners

Tokens per second that people measured on their own NVIDIA RTX PRO 6000 Blackwell, next to our estimate.

No one has measured Qwen2.5 72B on the NVIDIA RTX PRO 6000 Blackwell yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX PRO 6000 Blackwell? Add your real speed

One command times Qwen2.5 72B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- qwen2.5:72b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen2.5:72b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen2.5 72B comfortably

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run Qwen2.5 72B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run Qwen2.5 72B fully in VRAM at Q8_0 (near-lossless), using about 80.5 GB of the 96 GB available, at roughly 14 tokens/second.

How much VRAM does Qwen2.5 72B need?

About 47.4 GB at Q4_K_M with 8,192 tokens of context, and about 148.7 GB at full FP16 precision.

How fast is Qwen2.5 72B on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 14 tokens per second at Q8_0, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.