Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run Qwen3.8 Flash Next?

RTX PRO 6000 Blackwell × Qwen3.8 Flash Next8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q3_K_M88.8 GB of 96 GB
Weights 88 GBKV cache 0.2 GBRuntime 0.6 GB
QuantQ3_K_MNoticeably degraded
Speed~367tokens 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

Only just. Qwen3.8 Flash Next fits on the NVIDIA RTX PRO 6000 Blackwell at Q3_K_M, which costs noticeable quality. Expect about 367 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it in the cloud

Want full quality? Run Qwen3.8 Flash Next on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 quality360.8 GBToo big—
Q8_0Near-lossless192.1 GBToo big—
Q6_KExcellent148.4 GBToo big—
Q5_K_MVery good128.8 GBToo big—
Q4_K_MGood, most popular109.9 GBToo big—
Q3_K_MNoticeably degraded88.8 GBFits~367 tok/s
Q2_KHeavily degraded68.3 GBFits~478 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 Qwen3.8 Flash Next 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 Qwen3.8 Flash Next 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

Windows (PowerShell)

irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen3.8 Flash Next comfortably

Check Mac Studio M3 Ultra (256 GB) prices

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run Qwen3.8 Flash Next?

Only just. Qwen3.8 Flash Next fits on the NVIDIA RTX PRO 6000 Blackwell at Q3_K_M, which costs noticeable quality. Expect about 367 tokens/second. A card with more memory is a better experience.

How much VRAM does Qwen3.8 Flash Next need?

About 109.9 GB at Q4_K_M with 8,192 tokens of context, and about 360.8 GB at full FP16 precision.

How fast is Qwen3.8 Flash Next on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 367 tokens per second at Q3_K_M, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.