llamaperf
Submit

Qwen2.5 14B

on NVIDIA RTX 5080 · Ollama · 16,384 ctx

NVIDIA hardware
Oct 12, 2026
Throughput
94.6 t/s gen · 4864.7 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q4_K_M (GGUF)
VRAM reported
16 GB

Summary

User reports Qwen2.5 14B at 94.6 t/s generation and 4864.7 t/s prompt processing on one NVIDIA RTX 5080 16GB. Setup is Ollama with Q4_K_M at a configured 16384-token context; the recorded prompt was 1674 tokens, not a full 16384-token prefill. The figures are medians of 3 fresh-prefill runs, with 256 target output tokens and a unique nonce per repetition to avoid prompt-cache hits.