Benchmark result
tinyllama-1.1b-chat-v1.0 on NVIDIA GeForce RTX 2050 — 86.3 tok/s
Measured with LM Studio on October 20, 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 2050 · median 86.7 tok/s.
sort
- 187.1tok/s11.4LM Studio · Q8_0
- 286.3tok/s9.1LM Studio · Q8_0this run
Reproduce this run
toolLM Studio
modeltinyllama-1.1b-chat-v1.0 (Q8_0)
context16,384
clientv0.4.96+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "tinyllama-1.1b-chat-v1.0" --tool "LM 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.