Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run Qwen3 Coder 30B-A3B?

RTX PRO 6000 Blackwell × Qwen3 Coder 30B-A3B8K context
YesRuns fully on the GPU
Memory at FP1662.4 GB of 96 GB
Weights 61 GBKV cache 0.8 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~163tokens per second
Max context256Kthe 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 Qwen3 Coder 30B-A3B fully in VRAM at FP16 (full quality), using about 62.4 GB of the 96 GB available, at roughly 163 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Qwen3 Coder 30B-A3B:

ollama run qwen3-coder:30b

Ollama's default download is Q4_K_M (about 19.9 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 Qwen3 Coder 30B-A3B 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 quality62.4 GBFits~163 tok/s
Q8_0Near-lossless33.8 GBFits~307 tok/s
Q6_KExcellent26.4 GBFits~397 tok/s
Q5_K_MVery good23.1 GBFits~458 tok/s
Q4_K_MGood, most popular19.9 GBFits~537 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~667 tok/s
Q2_KHeavily degraded12.8 GBFits~869 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 Qwen3 Coder 30B-A3B 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 Qwen3 Coder 30B-A3B 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 -- qwen3-coder:30b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen3-coder:30b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3 Coder 30B-A3B comfortably

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run Qwen3 Coder 30B-A3B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run Qwen3 Coder 30B-A3B fully in VRAM at FP16 (full quality), using about 62.4 GB of the 96 GB available, at roughly 163 tokens/second.

How much VRAM does Qwen3 Coder 30B-A3B need?

About 19.9 GB at Q4_K_M with 8,192 tokens of context, and about 62.4 GB at full FP16 precision.

How fast is Qwen3 Coder 30B-A3B on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 163 tokens per second at FP16, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.