Benchmark result
CHADROCK-35B-Ace-Saber-MTP-ROCmFPX-MoEQuality-7.07BPW — 49.2 tok/s
Measured with llama.cpp b11544-aed0d5fd9 on September 29, 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.
How this run compares
CHADROCK-35B-Ace-Saber-MTP-ROCmFPX-MoEQuality-7.07BPW on other hardware
- 51.1tok/s81.1Unknown hardware
- 49.2tok/s79.4Unknown hardwarethis run
Reproduce this run
toolllama.cpp b11544-aed0d5fd9
modelCHADROCK-35B-Ace-Saber-MTP-ROCmFPX-MoEQuality-7.07BPW
context65,536
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.82+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "CHADROCK-35B-Ace-Saber-MTP-ROCmFPX-MoEQuality-7.07BPW" --tool "llama.cpp"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.