Rent a GPU

Can the AMD Radeon RX 9060 XT 16GB run Qwen2.5 Coder 32B?

Radeon RX 9060 XT 16GB × Qwen2.5 Coder 32B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K15 GB of 16 GB
Weights 12.3 GBKV cache 2.1 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~16tokens per second
Max context10Ktokens 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 Coder 32B fits on the AMD Radeon RX 9060 XT 16GB at Q2_K, which costs noticeable quality. Expect about 16 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default qwen2.5-coder:32b download is Q4_K_M, which needs about 22.6 GB, more than the 16 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 RX 9060 XT 16GB

Run it in the cloud

Want full quality? Run Qwen2.5 Coder 32B 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 16 GB the AMD Radeon RX 9060 XT 16GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality68.3 GBToo big—
Q8_0Near-lossless37.6 GBToo big—
Q6_KExcellent29.6 GBToo big—
Q5_K_MVery good26.1 GBToo big—
Q4_K_MGood, most popular22.6 GBToo big—
Q3_K_MNoticeably degraded18.8 GBToo big—
Q2_KHeavily degraded15 GBFits~16 tok/s

Measured speed from real Radeon RX 9060 XT 16GB owners

Tokens per second that people measured on their own AMD Radeon RX 9060 XT 16GB, next to our estimate.

No one has measured Qwen2.5 Coder 32B on the AMD Radeon RX 9060 XT 16GB yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon RX 9060 XT 16GB? Add your real speed

One command times Qwen2.5 Coder 32B 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-coder:32b

Windows (PowerShell)

$env:GPUFIT_MODEL="qwen2.5-coder:32b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Qwen2.5 Coder 32B comfortably

Check RTX 3090 prices

Models that run well on the AMD Radeon RX 9060 XT 16GB

Frequently asked questions

Can AMD Radeon RX 9060 XT 16GB run Qwen2.5 Coder 32B?

Only just. Qwen2.5 Coder 32B fits on the AMD Radeon RX 9060 XT 16GB at Q2_K, which costs noticeable quality. Expect about 16 tokens/second. A card with more memory is a better experience.

How much VRAM does Qwen2.5 Coder 32B need?

About 22.6 GB at Q4_K_M with 8,192 tokens of context, and about 68.3 GB at full FP16 precision.

How fast is Qwen2.5 Coder 32B on the AMD Radeon RX 9060 XT 16GB?

Roughly 16 tokens per second at Q2_K, estimated from the AMD Radeon RX 9060 XT 16GB's 320 GB/s memory bandwidth.