Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run DeepSeek R1 0528 Qwen3 8B?

RTX PRO 6000 Blackwell × DeepSeek R1 0528 Qwen3 8B8K context
YesRuns fully on the GPU
Memory at FP1618.2 GB of 96 GB
Weights 16.4 GBKV cache 1.2 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~66tokens per second
Max context128Kthe 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 DeepSeek R1 0528 Qwen3 8B fully in VRAM at FP16 (full quality), using about 18.2 GB of the 96 GB available, at roughly 66 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts DeepSeek R1 0528 Qwen3 8B:

ollama run deepseek-r1:8b

Ollama's default download is Q4_K_M (about 6.8 GB here). You have room for FP16, which is full quality: 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 DeepSeek R1 0528 Qwen3 8B 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 quality18.2 GBFits~66 tok/s
Q8_0Near-lossless10.5 GBFits~124 tok/s
Q6_KExcellent8.5 GBFits~160 tok/s
Q5_K_MVery good7.6 GBFits~185 tok/s
Q4_K_MGood, most popular6.8 GBFits~217 tok/s
Q3_K_MNoticeably degraded5.8 GBFits~269 tok/s
Q2_KHeavily degraded4.9 GBFits~350 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 DeepSeek R1 0528 Qwen3 8B 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 DeepSeek R1 0528 Qwen3 8B 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 -- deepseek-r1:8b

Windows (PowerShell)

$env:GPUFIT_MODEL="deepseek-r1:8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run DeepSeek R1 0528 Qwen3 8B comfortably

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run DeepSeek R1 0528 Qwen3 8B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run DeepSeek R1 0528 Qwen3 8B fully in VRAM at FP16 (full quality), using about 18.2 GB of the 96 GB available, at roughly 66 tokens/second.

How much VRAM does DeepSeek R1 0528 Qwen3 8B need?

About 6.8 GB at Q4_K_M with 8,192 tokens of context, and about 18.2 GB at full FP16 precision.

How fast is DeepSeek R1 0528 Qwen3 8B on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 66 tokens per second at FP16, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.