Benchmark result
cyber-tiel-coder-35b-a3b-mtp on AMD Radeon RX 7900 XTX — 113.6 tok/s
Measured with LM Studio on October 1, 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
3rd fastest of 4 runs of this model on AMD Radeon RX 7900 XTX · median 114.2 tok/s.
sort
- 1118.1tok/s86.0LM Studio · IQ3_XXS
- 2114.8tok/s75.8LM Studio · IQ3_XXS
- 3113.6tok/s70.7LM Studio · IQ3_XXSthis run
- 4113.5tok/s82.0LM Studio · IQ3_XXS
Reproduce this run
toolLM Studio
modelcyber-tiel-coder-35b-a3b-mtp (IQ3_XXS)
context8,192
thinkingon
clientv0.4.85+101
Set those in LM Studio, then:
llm-benchmark benchmark --model "cyber-tiel-coder-35b-a3b-mtp" --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.