Benchmark result
inclusionAI/Ling-3.0-tiny-GGUF on NVIDIA GeForce RTX 4070 — 193.5 tok/s
Measured with Unsloth Studio on October 29, 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 3 runs of this model on NVIDIA GeForce RTX 4070 · median 193.5 tok/s.
sort
- 1249.2tok/s47.9Unsloth Studio · Q6_K · KV q4_0
- 2193.5tok/s58.7Unsloth Studio · Q6_K · KV q4_0this run
- 3189.3tok/s63.4Unsloth Studio · Q6_K · KV q4_0
inclusionAI/Ling-3.0-tiny-GGUF on other hardware
Reproduce this run
toolUnsloth Studio
modelinclusionAI/Ling-3.0-tiny-GGUF (Q6_K)
context131,072
kv cacheq4_0
thinkingon
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.98+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "inclusionAI/Ling-3.0-tiny-GGUF" --tool "Unsloth Studio"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.