Skip to content

Can Radeon RX 7900 XT run GLM-4.7-Flash?

Tight: GGUF Q4_K_M needs 19.5 GB at 4K, batch 1; headroom 0.5 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 Q4_K_M19.5TightVerified file
GGUF Q8_033.5Does not fitVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K19.5Tight
16K20.2Tight
32K21.1Does not fit
128K26.6Does not fit

Generation speed

GGUF Q4_K_M: 456 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs