Skip to content

Can Tesla P100 16G run LFM2.5 8B-A1B?

Comfortable: GGUF Q8_0 needs 9.5 GB at 4K, batch 1; headroom 6.5 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_M5.4ComfortableVerified file
GGUF Q5_K_M6.4ComfortableVerified file
GGUF Q8_09.5ComfortableVerified file

Context capacity · GGUF Q8_0

ContextTotal GBVerdict
4K9.5Comfortable
16K9.6Comfortable
32K9.8Comfortable

Generation speed

GGUF Q8_0: 483 tok/s · Bandwidth ceiling (not measured)

Other model / GPU pairs