Benchmark result
SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact on NVIDIA GeForce RTX 3050 — 33.9 tok/s
Measured with llama.cpp manual on November 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; 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 NVIDIA GeForce RTX 3050 · median 34.6 tok/s.
sort
- 135.4tok/s80.2llama.cpp
- 233.9tok/s78.5llama.cppthis run
Reproduce this run
toolllama.cpp manual
modelSC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact
context65,536
think limitnone
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact" --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.