Benchmark result
mudler/Qwen3.6-35B-A3B-APEX-MTP-GGUF on Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 — 31.5 tok/s
Measured with llama.cpp b10636-4d19b2876 on September 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
3rd fastest of 4 runs of this model on Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 · median 31.6 tok/s.
sort
- 131.8tok/s69.3llama.cpp
- 231.7tok/s63.7llama.cpp
- 331.5tok/s68.1llama.cppthis run
- 431.5tok/s66.2llama.cpp
Reproduce this run
toolllama.cpp b10636-4d19b2876
modelmudler/Qwen3.6-35B-A3B-APEX-MTP-GGUF
context262,144
thinkingoff
clientv0.4.46+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "mudler/Qwen3.6-35B-A3B-APEX-MTP-GGUF" --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.