ModelGemma-4-26B-A4B / Gemma 4 26B
Gemma-4-26B-A4B-it
A sparse mixture-of-experts instruction-tuned model in Google's Gemma series, with 26B total parameters and 4B active parameters. It is one of the competing models positioned against LFM2.5-24B-A2B.
Timeline (last 90 days)
Oct 14
LFM2.5-24B-A2B outperforms Qwen3.6-35B-A3B, Gemma-4-26B-A4B-it, and Nemotron-3.5-Lightning (30B-A3B) on multiple instruction-following and agentic benchmarks, but lags on knowledge-intensive benchmarks such as SWE-Bench Verified and GPQA Diamond.
Unverified50%