Benchmark result

iq3_s on NVIDIA GeForce RTX 3060 — 41.6 tok/s

Measured with OpenAI-compatible manual on October 25, 2026.

What the model built

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

iq3_s on other hardware

56.1tok/s85.1AMD Radeon RX 7900 XTX

Reproduce this run

toolOpenAI-compatible manual

modeliq3_s

context65,536

clientv0.4.98+102

Set those in OpenAI-compatible, then:

llm-benchmark benchmark --model "iq3_s" --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.