Skip to content

Can Radeon RX 7900 XT run Hy-Memory-30B-A3B?

Comfortable: GGUF Q3_K_M needs 15.5 GB at 4K, batch 1; headroom 4.5 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 Q3_K_M15.5ComfortableVerified file
GGUF Q4_K_M19.5TightVerified file
GGUF Q6_K26.2Does not fitVerified file
GGUF Q8_033.8Does not fitVerified file
GGUF Q8_0-expsIQ2_XXS9.9ComfortableVerified file
GGUF Q8_0-expsIQ1_M8.8ComfortableVerified file

Context capacity · GGUF Q3_K_M

ContextTotal GBVerdict
4K15.5Comfortable
16K16.7Comfortable
32K18.4Tight
128K28.3Does not fit

Generation speed

GGUF Q3_K_M: 585 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs