Benchmark result
Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED on AMD Radeon RX 9070/9070 XT/9070 GRE — 76.4 tok/s
Measured with OpenAI-compatible manual on October 23, 2026.
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
2nd fastest of 2 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 77.1 tok/s.
sort
- 177.9tok/s83.4OpenAI-compatible
- 276.4tok/s78.4OpenAI-compatiblethis run
Reproduce this run
toolOpenAI-compatible manual
modelTiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED
context65,536
thinkingoff
clientv0.4.97+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1-RECLAIMED" --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.