Skip to content
llm-speed

Qwen3-Coder-Next vs Qwen2.5-Coder-32B-Instruct

Side-by-side decode tok/s, prefill tok/s, and TTFT for Qwen3-Coder-Next and Qwen2.5-Coder-32B-Instruct, sourced from community-submitted runs of the llm-speed suite. Every number on this page links back to the run it came from.

model
Qwen3-Coder-Next
Qwen · 80B-A3B
View Qwen3-Coder-Next page →
model
Qwen2.5-Coder-32B-Instruct
Qwen · 32B
View Qwen2.5-Coder-32B-Instruct page →

No overlapping Qwen3-Coder-Next ↔ Qwen2.5-Coder-32B-Instruct benchmarks yet.

We don't have a submitted run that covers both sides of this comparison yet. Run the suite on either side to populate this page:

$ pipx install llm-speed && llm-speed bench

See also: Qwen3-Coder-Next benchmarks · Qwen2.5-Coder-32B-Instruct benchmarks · All hardware · All models · Methodology