MicroLLM Lab – Try 7 tiny LLM's in the browser
MicroLLM Lab allows users to try out seven tiny LLMs directly in their browser. The platform focuses on benchmarking these models based on speed (tokens/s) and accuracy (pass rate on objective tests), with results displayed from runs on the user's machine. Users can write benchmarks in JavaScript, which are then eval()'d in the origin, and each check runs on the model's decoded text. The objective is to measure model performance, even if a 135M model fails.
Time & source
Times shown in UTC
Display time zone: UTC
Local time zone unavailable; showing UTC.
IngestedOffset at this time: UTC+0Sep 28, 2026, 20:00 UTC
- Ingested
- Sep 28, 2026, 20:00
- Source type
- Unclassified
Discussion trend
The percentage is based on collected discussion signal, not new comments or independent people. The curve only compares the same topic across time.
- Basis
- Running about 2.9× the median of this source's recent listed items
- Triggering item
- MicroLLM Lab – Try 7 tiny LLM's in the browser
- Metric comparison
- 265 vs median 91 (20 baseline samples)
- Detected
- 09/29, 16:00
Full text isn't available here.
Read at source →