Skip to content

Can Radeon RX 7900 XTX run K2 Horizon 32B?

Tight: GGUF Q4_K_M needs 23.1 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_M23.1TightVerified file
GGUF Q5_K_M26.9Does not fitVerified file
GGUF Q6_K30.9Does not fitVerified file
GGUF Q8_039.7Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K23.1Tight
16K26.4Does not fit
32K30.8Does not fit
128K57.2Does not fit

Generation speed

GGUF Q4_K_M: 48 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs