Benchmark result
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on AMD Radeon RX 9070/9070 XT/9070 GRE — 78.0 tok/s
Measured with OpenAI-compatible manual on October 23, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →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
8th fastest of 12 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 78.6 tok/s.
- 183.3tok/s86.0OpenAI-compatible
- 283.0tok/s87.7OpenAI-compatible
- 381.2tok/s84.0OpenAI-compatible
- 480.2tok/s87.0OpenAI-compatible
- 579.6tok/s79.8OpenAI-compatible
- 679.2tok/s87.9OpenAI-compatible
- 778.0tok/s82.2OpenAI-compatible
- 878.0tok/s79.4OpenAI-compatiblethis run
- 977.0tok/s80.3OpenAI-compatible
- 1076.9tok/s81.0OpenAI-compatible
- 1176.4tok/s79.3OpenAI-compatible
- 1273.3tok/s84.4OpenAI-compatible
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on other hardware
Reproduce this run
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1" --tool "OpenAI-compatible"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.