Benchmark result
ItachiSan/LiquidCode-2.5-24B-A2B-GGUF:Q4_K_M on NVIDIA GeForce RTX 2060 — 30.0 tok/s
Measured with llama.cpp b12184-c0ab6e5c0bab3fb21e6cb9d2371f3c41d85ea775 on November 8, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 2060 · median 28.0 tok/s.
sort
- 130.0tok/s52.4llama.cpp · Q4_K_Mthis run
- 226.0tok/s38.1llama.cpp · Q4_K_M
Reproduce this run
toolllama.cpp b12184-c0ab6e5c0bab3fb21e6cb9d2371f3c41d85ea775
modelItachiSan/LiquidCode-2.5-24B-A2B-GGUF:Q4_K_M (Q4_K_M)
context131,072
samplingtemperature 0.10000000149011612 · top_p 0.949999988079071 · top_k 50 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ItachiSan/LiquidCode-2.5-24B-A2B-GGUF:Q4_K_M" --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.