Skip to content

Can Radeon RX 9060 XT 16G run Qwen3-VL 30B-A3B Instruct?

Tight: GGUF Q3_K_M needs 15.1 GB at 4K, batch 1; headroom 0.9 GB.

Text input, FP16 KV cache, one card. Unified-memory capacity uses the GPU guide’s usable limit; negative headroom may require host offload. Speed source settings may differ from this 4K estimate.

Measured runs

No measured run for this pair. Sizing is an estimate, not a runtime test.

Quant memory at 4K

QuantTotal GBVerdictWeight sizing
GGUF Q4_K_M19.9Does not fitVerified file
GGUF Q3_K_M15.1TightVerified file
GGUF Q8_034.4Does not fitVerified file
AWQ INT416.4TightEstimated weights

Context capacity · GGUF Q3_K_M

ContextTotal GBVerdict
4K15.1Tight
16K16.4Tight
32K18.0Does not fit
128K27.9Does not fit

Generation speed

GGUF Q3_K_M: 243 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs