Skip to content

Can Radeon PRO W7900 48G run LFM2.5 24B-A2B?

Comfortable: GGUF Q8_0 needs 26.7 GB at 4K, batch 1; headroom 21.3 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_M15.3ComfortableVerified file
GGUF Q8_026.7ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K26.7Comfortable
16K27.0Comfortable
32K27.3Comfortable
128K29.4Comfortable

Generation speed

GGUF Q8_0: 349 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs