Google releases Gemma 4 open models
deepmind.google
Google releases Gemma 4 open models
1–10 of 507 posts
Re: Google releases Gemma 4 open models
#2Thinking / reasoning + multimodal + tool calling.
We made some quants at https://huggingface.co/collections/unsloth/gemma-4 for folks to run them - they work really well!
Guide for those interested: https://unsloth.ai/docs/models/gemma-4
Also note to use temperature = 1.0, top_p = 0.95, top_k = 64 and the EOS is "". "thought\n" is also used for the thinking trace!
Re: Google releases Gemma 4 open models
#3Really looking forward to testing and benchmarking this on my spam filtering benchmark. gemma-3-27b was a really strong model, surpassed later by gpt-oss:20b (which was also much faster). qwen models always had more variance.
Re: Google releases Gemma 4 open models
#4[flagged]
Re: Google releases Gemma 4 open models
#5It's good they still have non-instruction-tuned models.
Re: Google releases Gemma 4 open models
#6The benchmark comparisons to Gemma 3 27B on Hugging Face are interesting: The Gemma 4 E4B variant (https://huggingface.co/google/gemma-4-E4B-it) beats the old 27B in every benchmark at a fraction of parameters.
The E2B/E4B models also support voice input, which is rare.
Re: Google releases Gemma 4 open models
#7Best thing is that this is Apache 2.0 (edit: and they have base models available. Gemma3 was good for finetuning)
The sizes are E2B and E4B (following gemma3n arch, with focus on mobile) and 26BA4 MoE and 31B dense. The mobile ones have audio in (so I can see some local privacy focused translation apps) and the 31B seems to be strong in agentic stuff. 26BA4 stands somewhere in between, similar VRAM footprint, but much faster inference.
Re: Google releases Gemma 4 open models
#8Wow, 30B parameters as capable as a 1T parameter model?
Re: Google releases Gemma 4 open models
#9This is awesome! I will try to use them locally with opencode and see if they are usable inreplacement of claude code for basic tasks
Re: Google releases Gemma 4 open models
#10Featuring the ELO score as the main benchmark in chart is very misleading. The big dense Gemma 4 model does not seem to reach Qwen 3.5 27B dense model in most benchmarks. This is obviously what matters. The small 2B / 4B models are interesting and may potentially be better ASR models than specialized ones (not just for performances but since they are going to be easily served via llama.cpp / MLX and front-ends). Also interesting for "fast" OCR, given they are vision models as well. But other than that, the release is a bit disappointing.