Can Qwen3-VL 30B A3B Instruct run on AMD Instinct MI210 64GB?
YES — Runs Great
Qwen3-VL 30B A3B Instruct needs ~28.6 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q4_K_M quantization, expect ~132 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
132.4 tok/s
TTFT
1462 ms
Safe context
256K
Memory
28.6 GB / 64.0 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 | 132.4 tok/s | 798 ms | 256K |
| Coding | S | Runs well | 132.4 tok/s | 1462 ms | 256K |
| Agentic Coding | S | Runs well | 132.4 tok/s | 2127 ms | 256K |
| Reasoning | S | Runs well | 132.4 tok/s | 1728 ms | 256K |
| RAG | S | Runs well | 132.4 tok/s | 2659 ms | 256K |
Quantization options
How Qwen3-VL 30B A3B Instruct (30B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | A84 |
Q3_K_S | 3 | 14.7 GB | Low | A85 |
NVFP4 | 4 | 16.8 GB | Medium | A85 |
Q4_K_M | 4 | 18.3 GB | Medium | S85 |
Q5_K_M | 5 | 21.6 GB | High | S86 |
Q6_K | 6 | 24.6 GB | High | S87 |
Q8_0Best for your GPU | 8 | 32.1 GB | Very High | S89 |
F16 | 16 | 61.5 GB | Maximum | F0 |
Get started
Copy-paste commands to run Qwen3-VL 30B A3B Instruct on your machine.
Run
lms load Qwen3-VL-30B-A3B-Instruct && lms server startYour hardware
