Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google releases Gemma 4 open models

deepmind.google

Post reply on HN
Print view View original

271–280 of 507 posts

Re: Google releases Gemma 4 open models

#271

Post by evilduck »

kcb wrote: post #165
coder68 wrote: post #159

Earlier quoted context omitted.

120B would be great to have if you have it stashed away somewhere. GPT-OSS-120B still stands as one of the best (and fastest) open-weights models out there. A direct competitor in the same size range would be awesome. The closest recent release was Qwen3.5-122B-A10B.

Nemotron 3 Super was released recently. That's a direct competitor to gpt-oss-120b. https://developer.nvidia.com/blog/introducing-nemotron-3-sup...

In terms of ability, maybe, in terms of speed, it's not even close. Check out the Prompt Processing speeds between them: https://kyuz0.github.io/amd-strix-halo-toolboxes/

gpt-oss-120b is over 600 tokens/s PP for all but one backend.

nemotron-3-super is at best 260 tokens/s PP.

Comparing token generation, it's again like 50 tokens/sec vs 15 tokens/sec

That really bogs down agentic tooling. Something needs to be categorically better to justify halving output speed, not just playing in the margins.

Re: Google releases Gemma 4 open models

#272

Post by pxc »

echelon wrote: post #17
rvz wrote: post #11

Open weight models once again marching on and slowly being a viable alternative to the larger ones. We are at least 1 year and at most 2 years until they surpass closed models for everyday tasks that can be done locally to save spending on tokens.

> We are at least 1 year and at most 2 years until they surpass closed models for everyday tasks that can be done locally to save spending on tokens. Until they pass what closed models today can do. By that time, closed models will be 4 years ahead. Google would not be giving this away if they believed local open models could win. Google is doing this to slow down Anthropic, OpenAI, and the Chinese, knowing that in t…

If they pass what closed models today can do by much, they'll be "good enough" for what I want to do with them. I imagine that's true for many people.

Re: Google releases Gemma 4 open models

#274

Post by zobzu »

danielhanchen wrote: post #2

Thinking / 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!

neat, time to update my spam filter model hehe

Re: Google releases Gemma 4 open models

#275

Post by __mharrison__ »

canyon289 wrote: post #79
tjwebbnorfolk wrote: post #74

Earlier quoted context omitted.

Will larger-parameter versions be released?

We are always figuring out what parameter size makes sense. The decision is always a mix between how good we can make the models from a technical aspect, with how good they need to be to make all of you super excited to use them. And its a bit of a challenge what is an ever changing ecosystem. I'm personally curious is there a certain parameter size you're looking for?

My sweet spot is something that runs on less than 128gb.

(I have a DGX Spark, and MBP w/ 128gb).

Re: Google releases Gemma 4 open models

#276

Post by redman25 »

coder543 wrote: post #135
canyon289 wrote: post #79

Earlier quoted context omitted.

We are always figuring out what parameter size makes sense. The decision is always a mix between how good we can make the models from a technical aspect, with how good they need to be to make all of you super excited to use them. And its a bit of a challenge what is an ever changing ecosystem. I'm personally curious is there a certain parameter size you're looking for?

For the many DGX Spark and Strix Halo users with 128GB of memory, I believe the ideal model size would probably be a MoE with close to 200B total parameters and a low active count of 3B to 10B. I would personally love to see a super sparse 200B A3B model, just to see what is possible. These machines don't have a lot of bandwidth, so a low active count is essential to getting good speed, and a high total parameter cou…

200a10b please, 200a3b is too little active to have good intelligence IMO and 10b is still reasonably fast.

Re: Google releases Gemma 4 open models

#277

Post by emidoots »

coder543 wrote: post #205
swalsh wrote: post #199

I gave the same prompt (a small rust project that's not easy, but not overly sophisticated) to both Gemma-4 26b and Qwen 3.5 27b via OpenCode. Qwen 3.5 ran for a bit over an hour before I killed it, Gemma 4 ran for about 20 minutes before it gave up. Lots of failed tool calls. I asked codex to write a summary about both code bases. "Dev 1" Qwen 3.5 "Dev 2" Gemma 4 Dev 1 is the stronger engineer overall. They showed b…

There are issues with the chat template right now[0], so tool calling does not work reliably[1]. Every time people try to rush to judge open models on launch day... it never goes well. There are ~always bugs on launch day. [0]: https://github.com/ggml-org/llama.cpp/pull/21326 [1]: https://github.com/ggml-org/llama.cpp/issues/21316

was just merged

Re: Google releases Gemma 4 open models

#278

Post by coder543 »

emidoots wrote: post #277
coder543 wrote: post #205

Earlier quoted context omitted.

There are issues with the chat template right now[0], so tool calling does not work reliably[1]. Every time people try to rush to judge open models on launch day... it never goes well. There are ~always bugs on launch day. [0]: https://github.com/ggml-org/llama.cpp/pull/21326 [1]: https://github.com/ggml-org/llama.cpp/issues/21316

was just merged

It was just an example of a bug, not that it was the only bug. I’ve personally reported at least one other for Gemma 4 on llama.cpp already.

In a few days, I imagine that Gemma 4 support should be in better shape.

Re: Google releases Gemma 4 open models

#280

Post by redman25 »

petu wrote: post #261
swalsh wrote: post #199

I gave the same prompt (a small rust project that's not easy, but not overly sophisticated) to both Gemma-4 26b and Qwen 3.5 27b via OpenCode. Qwen 3.5 ran for a bit over an hour before I killed it, Gemma 4 ran for about 20 minutes before it gave up. Lots of failed tool calls. I asked codex to write a summary about both code bases. "Dev 1" Qwen 3.5 "Dev 2" Gemma 4 Dev 1 is the stronger engineer overall. They showed b…

Qwen 3.5 27B is dense, so (I think) should be compared to Gemma 4 31B. Or Gemma-4 26B(-A4B) should be compared to Qwen 3.5 35B(-A3B)

Exactly, compare MoE with MoE and dense with dense otherwise it's apples and oranges.
Post reply on HN