Hi all!
I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can
Google releases Gemma 4 open models
51–60 of 507 posts
Re: Google releases Gemma 4 open models
#52[flagged]
Re: Google releases Gemma 4 open models
#53Earlier quoted context omitted.
Not OP but one example is that recent VL models are more than sufficient for analyzing your local photo albums/images for creating metadata / descriptions / captions to help better organize your library.
Any pointers on some local VLMs to start with?
You could try Gemma4 :D
Re: Google releases Gemma 4 open models
#54Qwen: Hold my beer https://news.ycombinator.com/item?id=47615002
The Qwen Plus models should be compared to Gemini, not Gemma.
Re: Google releases Gemma 4 open models
#55Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can
How is the performance for Japanese, voice in particular?
Re: Google releases Gemma 4 open models
#56Gemma vs Gemini? I am only a casual AI chatbot user, I use what gives me the most and best free limits and versions.
Gemma is only 10s of billion parameters, Gemini is 100s.
Re: Google releases Gemma 4 open models
#57Thinking / 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!
Daniel, your work is changing the world. More power to you.
I setup a pipeline for inference with OCR, full text search, embedding and summarization of land records dating back 1800s. All powered by the GGUF's you generate and llama.cpp. People are so excited that they can now search the records in multiple languages that a 1 minute wait to process the document seems nothing. Thank you!
Re: Google releases Gemma 4 open models
#58Even with search grounding, it scored a 2.5/5 on a basic botanical benchmark. It would take much longer for the average human to do a similar write-up, but they would likely do better than 50% hallucination if they had access to a search engine.
Even multimodal models are still really bad when it comes to vision. The strength is still definitely language.
Re: Google releases Gemma 4 open models
#59Thinking / 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!
Daniel, your work is changing the world. More power to you. I setup a pipeline for inference with OCR, full text search, embedding and summarization of land records dating back 1800s. All powered by the GGUF's you generate and llama.cpp. People are so excited that they can now search the records in multiple languages that a 1 minute wait to process the document seems nothing. Thank you!
Oh appreciate it!
Oh nice! That sounds fantastic! I hope Gemma-4 will make it even better! The small ones 2B and 4B are shockingly good haha!
Re: Google releases Gemma 4 open models
#60Featuring 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…
I can't find what ELO score specifically the benchmark chart is referring to, it's just labeled "Elo Score". It's not Codeforces ELO as that Gemma 4 31B has 2150 for that which would be off the given chart.