Skip to content

Can RTX 4060 Ti 8G run LFM2.5 8B-A1B?

Comfortable: GGUF Q5_K_M needs 6.4 GB at 4K, batch 1; headroom 1.6 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_M5.4ComfortableVerified file
GGUF Q5_K_M6.4ComfortableVerified file
GGUF Q8_09.5Does not fitVerified file

Context capacity · GGUF Q5_K_M

ContextTotal GBVerdict
4K6.4Comfortable
16K6.5Comfortable
32K6.7Comfortable

Generation speed

GGUF Q5_K_M: 284 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs