Benchmark result
inclusionAI/Ling-3.0-tiny-GGUF:Q4_K_M on NVIDIA GeForce RTX 2060 — 33.0 tok/s
Measured with OpenAI-compatible manual on September 21, 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
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 2060 · median 44.3 tok/s.
sort
- 155.7tok/s58.1llama.cpp · Q4_K_M
- 233.0tok/s50.9OpenAI-compatible · Q4_K_Mthis run
Reproduce this run
toolOpenAI-compatible manual
modelinclusionAI/Ling-3.0-tiny-GGUF:Q4_K_M (Q4_K_M)
context8,192
clientv0.4.80+98
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "inclusionAI/Ling-3.0-tiny-GGUF:Q4_K_M" --tool "OpenAI-compatible"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.