Skip to content

Can RTX 5090 run GLM-4.7-Flash?

Comfortable: GGUF Q4_K_M needs 19.5 GB at 4K, batch 1; headroom 12.5 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_M19.5ComfortableVerified file
GGUF Q8_033.5TightVerified file

Context capacity · GGUF Q4_K_M

ContextTotal GBVerdict
4K19.5Comfortable
16K20.2Comfortable
32K21.1Comfortable
128K26.6Comfortable

Generation speed

GGUF Q4_K_M: 1021 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs