Skip to content
llm-speed

Qwen2.5-Coder-32B-Instruct vs DeepSeek-V3

Side-by-side decode tok/s, prefill tok/s, and TTFT for Qwen2.5-Coder-32B-Instruct and DeepSeek-V3, sourced from community-submitted runs of the llm-speed suite. Every number on this page links back to the run it came from.

model
Qwen2.5-Coder-32B-Instruct
Qwen · 32B
View Qwen2.5-Coder-32B-Instruct page →
model
DeepSeek-V3
DeepSeek · 671B-A37B
View DeepSeek-V3 page →

No overlapping Qwen2.5-Coder-32B-Instruct ↔ DeepSeek-V3 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: Qwen2.5-Coder-32B-Instruct benchmarks · DeepSeek-V3 benchmarks · All hardware · All models · Methodology