Can Qwen 3 30B A3B run on AMD Instinct MI325X 256GB?
YES — Runs Great
Qwen 3 30B A3B needs ~46.6 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~662 tok/s.
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
662.3 tok/s
TTFT
350 ms
Safe context
131K
Memory
46.6 GB / 256.0 GB
Memory breakdown
See how fast it feels
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 662.3 tok/s | 350 ms | 131K |
| Coding | S | Runs well | 662.3 tok/s | 350 ms | 131K |
| Agentic Coding | S | Runs well | 662.3 tok/s | 425 ms | 131K |
| Reasoning | S | Runs well | 662.3 tok/s | 350 ms | 131K |
| RAG | S | Runs well | 662.3 tok/s | 531 ms | 131K |
Quantization options
How Qwen 3 30B A3B (30.5B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.9 GB | Low | A77 |
Q3_K_S | 3 | 14.9 GB | Low | A77 |
NVFP4 | 4 | 17.1 GB | Medium | A77 |
Q4_K_M | 4 | 18.6 GB | Medium | A77 |
Q5_K_M | 5 | 22.0 GB | High | A78 |
Q6_K | 6 | 25.0 GB | High | A78 |
Q8_0 | 8 | 32.6 GB | Very High | A78 |
F16Best for your GPU | 16 | 62.5 GB | Maximum | A81 |
Get started
Copy-paste commands to run Qwen 3 30B A3B on your machine.
Run
ollama run qwen3:30b-a3bYour hardware
More models your AMD Instinct MI325X 256GB can run
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 👁 Alibaba Qwen 3.5 397B A17B | 397B | A | 39.2 tok/s | |
| 👁 Mistral Devstral 2 123B Instruct | 123B | S | 63.5 tok/s | |
| 👁 Alibaba Qwen 3.5 122B A10B | 122B | S | 176.1 tok/s | |
| 👁 DeepSeek DeepSeek V4 Flash | 284B | S | 94.4 tok/s | |
| 👁 Alibaba Qwen 3.6 35B A3B | 35B | S | 556.6 tok/s |
