LFM2.5-24B-A2B

on RTX A4000

140.0

tok/sdecode

RTX A4000 (16GB) + AMD EPYC 7402P 24-Core Processor (24c) + 126GB

rank in tier

1/1RTX A4000 runs

best workload

chat-short

where the rig flew

slowest workload

agent-trace139.4 tok/s

where the rig struggled

backend

llama.cppllama.cpp is the universal backend — broad model support, modest speed ceiling.

faster than

Qwen2.5-7B-Instruct-4bit on M3 Ultra139.6 tok/s
qwen2.5-coder on RTX 3090139.2 tok/s
Qwen2.5-Coder-7B-Instruct-4bit on M3 Ultra138.6 tok/s

This is a shareable view of one signed llm-speed suite-suite-v1 run. Numbers are not edited. The raw record has every workload, the public key, and the fingerprint hash.