Skip to content

Can Radeon RX 7900 XTX run Qwen3.6 27B?

Comfortable: GGUF Q4_K_M needs 19.1 GB at 4K, batch 1; headroom 4.9 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_M19.1ComfortableVerified file
GGUF Q5_K_M22.2TightVerified file
GGUF Q8_030.7Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K19.1Comfortable
16K19.9Comfortable
32K21.0Comfortable
128K27.6Does not fit

Generation speed

GGUF Q4_K_M: 35–47 tok/s · Derived range

Other model / GPU pairs