Rent a GPU

Can the AMD Radeon AI PRO R9700 run Qwen2.5 72B?

Radeon AI PRO R9700 × Qwen2.5 72B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K30.5 GB of 32 GB
Weights 27.3 GBKV cache 2.7 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~14tokens per second
Max context11Ktokens that fit at Q2_K
  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. Qwen2.5 72B fits on the AMD Radeon AI PRO R9700 at Q2_K, which costs noticeable quality. Expect about 14 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwen2.5:72b download is Q4_K_M, which needs about 47.4 GB, more than the 32 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the Radeon AI PRO R9700

Run it in the cloud

Want full quality? Run Qwen2.5 72B 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 32 GB the AMD Radeon AI PRO R9700 can use.

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

Measured speed from real Radeon AI PRO R9700 owners

Tokens per second that people measured on their own AMD Radeon AI PRO R9700, next to our estimate.

No one has measured Qwen2.5 72B on the AMD Radeon AI PRO R9700 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon AI PRO R9700? 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

Check Mac Studio M4 Max (64 GB) prices

Models that run well on the AMD Radeon AI PRO R9700

Frequently asked questions

Can AMD Radeon AI PRO R9700 run Qwen2.5 72B?

Only just. Qwen2.5 72B fits on the AMD Radeon AI PRO R9700 at Q2_K, which costs noticeable quality. Expect about 14 tokens/second. A card with more memory is a better experience.

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 AMD Radeon AI PRO R9700?

Roughly 14 tokens per second at Q2_K, estimated from the AMD Radeon AI PRO R9700's 640 GB/s memory bandwidth.