Written by Jakub Rusinowski · Last updated August 15, 2026
Yes. Qwen 3 30B-A3B (MoE) needs 18.4 GB at Q4_K_M and the AMD Radeon RX 7900 XTX has 24 GB, leaving about 5.6 GB of headroom, at roughly 136 tok/s (estimated) with room for up to 32K of context.
| Model | Qwen 3 30B-A3B (MoE) |
| Parameters | 30B (3B active) |
| Quantization | Q4_K_M |
| VRAM needed | 18.4 GB |
| AMD Radeon RX 7900 XTX VRAM | 24 GB |
| Verdict | Runs |
| Max context | 32K |
| Estimated speed | ~136 tok/s |
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
Running Qwen 3 30B-A3B (MoE) on this card:
At 2 hrs/day, buying (~$999) beats renting at $0.34/hr after about 4.1 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
All Qwen 3 sizes on the AMD Radeon RX 7900 XTX | VRAM calculator for Qwen 3 30B-A3B (MoE) | AMD Radeon RX 7900 XTX GPU page | Check your hardware