Benchmark result
Tiel-Coder-35B-A3B-Q4_K_S on AMD Radeon RX 7900 XTX — 166.6 tok/s
Measured with llama.cpp b304-1443bbd on September 5, 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
1st fastest of 5 runs of this model on AMD Radeon RX 7900 XTX · median 162.1 tok/s.
sort
- 1166.6tok/s84.9llama.cpp · Q4_K_Sthis run
- 2166.2tok/s83.8llama.cpp · Q4_K_S
- 3162.1tok/s85.1llama.cpp · Q4_K_S
- 4159.5tok/s87.5llama.cpp · Q4_K_S
- 5157.6tok/s84.2llama.cpp · Q4_K_S
Reproduce this run
toolllama.cpp b304-1443bbd
modelTiel-Coder-35B-A3B-Q4_K_S (Q4_K_S)
context65,536
thinkingon
clientv0.4.46+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-Q4_K_S" --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.