llamaperf
Nov 15, 2026
Throughput
37.0 t/s gen

Use cases

agentictool-use

Summary

User reports LFM2.5-24B-A2B at about 37 t/s at zero context on an AMD Radeon 780M iGPU. No engine, quant or context settings are stated beyond the GGUF build linked. User says it is not a coding model but a task executor, and that it pairs well with Hermes for handing off low-to-mid complexity tasks.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

LFM2.5 24B · 2.5B active at 4-bit by hardware

Bars are medians on one scale, 0 to 52.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Models most run on the AMD Radeon 780M

Bars are medians on one scale, 0 to 25.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Everything reported on the AMD Radeon 780M →Every LFM2.5 report →