Benchmark result
Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL on AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 XT +1 more — 36.1 tok/s
Measured with llama.cpp b10629-eab8ee41f on August 26, 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
1st fastest of 3 runs of this model on AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 XT +1 more · Multi-GPU · median 35.0 tok/s.
sort
- 136.1tok/s85.8llama.cpp · Q6_Kthis run
- 235.0tok/s87.6llama.cpp · Q6_K
- 334.2tok/s83.1llama.cpp · Q6_K
Reproduce this run
toolllama.cpp b10629-eab8ee41f
modelTiel-Coder-35B-A3B-MTP-UD-Q6_K_XL (Q6_K)
context85,248
thinkingon
clientv0.4.44+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL" --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.