Rent a GPU

Can the AMD Radeon RX 7900 XTX run Qwen3 Coder 30B-A3B?

Radeon RX 7900 XTX × Qwen3 Coder 30B-A3B8K context
YesRuns fully on the GPU
Memory at Q5_K_M23.1 GB of 24 GB
Weights 21.7 GBKV cache 0.8 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~245tokens per second
Max context16Ktokens that fit at Q5_K_M
  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 AMD Radeon RX 7900 XTX can run Qwen3 Coder 30B-A3B fully in VRAM at Q5_K_M (very good), using about 23.1 GB of the 24 GB available, at roughly 245 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 Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Radeon RX 7900 XTX

Run it in the cloud

No AMD Radeon RX 7900 XTX? 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 24 GB the AMD Radeon RX 7900 XTX can use.

QuantQualityMemoryFits?Speed
FP16Full quality62.4 GBToo big—
Q8_0Near-lossless33.8 GBToo big—
Q6_KExcellent26.4 GBToo big—
Q5_K_MVery good23.1 GBFits~245 tok/s
Q4_K_MGood, most popular19.9 GBFits~288 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~357 tok/s
Q2_KHeavily degraded12.8 GBFits~465 tok/s

Measured speed from real Radeon RX 7900 XTX owners

Tokens per second that people measured on their own AMD Radeon RX 7900 XTX, next to our estimate.

No one has measured Qwen3 Coder 30B-A3B on the AMD Radeon RX 7900 XTX yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon RX 7900 XTX? 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 AMD Radeon RX 7900 XTX

Frequently asked questions

Can AMD Radeon RX 7900 XTX run Qwen3 Coder 30B-A3B?

Yes. The AMD Radeon RX 7900 XTX can run Qwen3 Coder 30B-A3B fully in VRAM at Q5_K_M (very good), using about 23.1 GB of the 24 GB available, at roughly 245 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 AMD Radeon RX 7900 XTX?

Roughly 245 tokens per second at Q5_K_M, estimated from the AMD Radeon RX 7900 XTX's 960 GB/s memory bandwidth.