Skip to content
llm-speed
wrapped·Jul 02, 2026
/r/r_6ahy-dq0f_0
your run

qwen2.5-coder

69.2
tok/sdecode
RTX 3090 (24GB)
rank in tier
14/25RTX 3090 runstop 56%
best workload
chat-short
where the rig flew
slowest workload
agent-trace63.6 tok/s
where the rig struggled
backend
ollamaollama is llama.cpp under the hood; pure llama.cpp tends to nudge a few % faster.
faster than
  • starcoder2-15b-4bit on M3 Ultra64.2 tok/s
  • Ripple-65B-Preview-AD on RTX 509056.3 tok/s
  • Muse-Glimmer-30B-ctx8k on RTX 409053.7 tok/s
share
69.2 tok/s on RTX 3090 running qwen2.5-coder — top 56% of RTX 3090 runs. Signed benchmark via llm-speed.
https://llm-speed.com/wrapped/r_6ahy-dq0f_0

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.