# Gemma 4 Que Times - LiveKit Inference

**URL:** <https://community.livekit.io/t/gemma-4-que-times-livekit-inference/1876>\
**Category:** Agents\
**Tags:** llm, livekit-inference\
**Created:** [August 17, 2026, 10:39pm UTC](https://community.livekit.io/t/gemma-4-que-times-livekit-inference/1876 "2026-08-17T22:39:55Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![Kaushal\_Shah](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/kaushal_shah/32/1237_2.png) [@Kaushal\_Shah](https://community.livekit.io/u/Kaushal_Shah)\
**Post date:** [August 19, 2026, 2:24pm UTC](https://community.livekit.io/t/gemma-4-que-times-livekit-inference/1876/6 "2026-08-19T14:24:28Z")

</div>

> [@LiveKit Inference timeouts happening since past 2 weeks](https://community.livekit.io/t/livekit-inference-timeouts-happening-since-past-2-weeks/1718/61):
>
> @CWilson @Adrian_Cowham Thanks, we can mark this as solved! The timeout errors are solved. However, I’m seeing high TTFS and TTFT than before for gemma. Looking at benchmarks, the TTFT seems to be getting progressively higher each day. I was expecting consistently fast performance, is there a way to optimize this, or should I open a new post to discuss it?

i have raised similar issue here.

> **[LLM Latency Benchmarks | LiveKit](https://livekit.com/benchmarks/latency)**
>
> Live latency and throughput benchmarks for the LLMs available through LiveKit Inference.

Its probably that gemma is used more often and is receiving more traffic and latency is increasing.

---

_[View the full topic](https://community.livekit.io/t/gemma-4-que-times-livekit-inference/1876)._