Skip to content
llm-speed

Qwen3-Coder-30B-A3B-Instruct vs Codestral-22B-v0.1

Signed, community-submitted decode tok/s, prefill, and TTFT for Qwen3-Coder-30B-A3B-Instruct vs Codestral-22B-v0.1 — every number links to the run it came from.

Verdict

On the RTX 5090 (32GB), Qwen3-Coder-30B-A3B-Instruct decodes at 260 tok/s versus 100 tok/s for Codestral-22B-v0.1, 2.6× faster. Across 2 hardware configs measured on both, Qwen3-Coder-30B-A3B-Instruct is faster on 2 of 2. Every cell in the table below links to the submitted run it came from.

model
Qwen3-Coder-30B-A3B-Instruct
Qwen · 30B-A3B
View Qwen3-Coder-30B-A3B-Instruct page →
model
Codestral-22B-v0.1
Mistral · 22B
View Codestral-22B-v0.1 page →

Hardware with data on both models

HardwareQwen3-Coder-30B-A3B-Instruct decodeCodestral-22B-v0.1 decodeΔSource runs
RTX 5090 (32GB)259.9tok/s100.3tok/s+159.6r_c7qyvvmmsv1 · r_4q040m4scic
M3 Ultra (60-core GPU)112.2tok/s47.49tok/s+64.7r_fpsca03u2o_ · r_79dvtag5fd_

See also: Qwen3-Coder-30B-A3B-Instruct benchmarks · Codestral-22B-v0.1 benchmarks · All hardware · All models · Methodology