Benchmark result
unsloth/flint-GGUF:UD-Q4_K_XL on Apple M5 Max — 200.9 tok/s
Measured with splash manual on November 14, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
unsloth/flint-GGUF:UD-Q4_K_XL on other hardware
Reproduce this run
toolsplash manual
modelunsloth/flint-GGUF:UD-Q4_K_XL (Q4_K)
context131,972
clientv0.4.99+102
Set those in splash, then:
llm-benchmark benchmark --model "unsloth/flint-GGUF:UD-Q4_K_XL" --tool "splash"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.