Benchmark result

Cyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on AMD Radeon RX 7900 XTX — 44.7 tok/s

Measured with lm-studio manual on October 2, 2026.

What the model built

The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.

How this run compares

Cyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on other hardware

21.9tok/s84.3Intel Graphics
21.3tok/s74.6Intel Graphics
21.2tok/s83.3Intel Graphics
20.3tok/s82.6Intel Graphics
14.0tok/s83.2Intel Graphics

Reproduce this run

toollm-studio manual

modelCyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1

context80,000

thinkingon

clientv0.4.85+101

Set those in lm-studio, then:

llm-benchmark benchmark --model "Cyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1" --tool "lm-studio"

The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.