Skip to content

Can Radeon RX 7900 XT run Xing4.0 29B-A4B?

Comfortable: GGUF Q3_K_M needs 17.0 GB at 4K, batch 1; headroom 3.0 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 Q8_034.9Does not fitVerified file
GGUF Q6_K28.6Does not fitVerified file
GGUF Q5_K_M25.3Does not fitVerified file
GGUF Q4_K_M21.2Does not fitVerified file
GGUF IQ4_XS19.0TightVerified file
GGUF Q3_K_M17.0ComfortableVerified file
GGUF IQ3_XXS15.3ComfortableVerified file
GGUF Q2_K13.6ComfortableVerified file
GGUF IQ2_XXS11.0ComfortableVerified file

Context capacity · GGUF Q3_K_M

ContextTotal GBVerdict
4K17.0Comfortable
16K17.6Comfortable
32K18.4Tight
128K23.0Does not fit

Generation speed

GGUF Q3_K_M: 409 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs