what are limits of using these? how many api calls can i send them per month?

How can I know which model am using

How can I know which model am using

at the bottom of your screen:

Out of all these models, Gemma, which was recently released, has the newest information about .NET. However, I don't know which one has the most accurate answers regarding coding

Gemma seems really biased. With web search on, it says that it doesn't have access to recent information asking it almost anything about recent events. But when I ask it about recent events with Google, I get responses with the recent events.

apparently gemma cannot code?

Gemma is just like Google's Gemini series models, it have a very strong moral limit put on, any operation that may related to file operation, access that might be deep, would be censored and refused to reply.
So even there are solution for such things in its training data, it will just be filtered and ignored.
But still didn't test the coding accuracy that doesn't related to these kind of "dangerous" operations

The thinking process of the Deepseek model is outputted as part of the answer, instead of being placed in the thinking box. Would the Huggingface IT team fix the problem? Thank you.

"IT team???!!" Huggingface researchers be like👇🤣🤣🤣🤣

Any plan to add new mistral small 3?

Request of New Modell and addons for the reasoning Model.

Plesse add two new deepsek Models, so a V3 Model 70B and the Deepseek r1 70B.
Why is momently only a 30B Model Deepseek r1 online?

I have just discovered openrouter 🥳 and while it doesnt have the ultra custom LLMs of huggingface ggufs, it has tons of free opensource LLMs, tons, and a bunch of closed source ones. my new favorite opens are Mistral Small 3 24B and Rogue Rose 103B, Llama 3.3 70B is still my main, you can access Gemini flash 2.0 exp free as well. If hugging chat is lagging behind with 6 LLMs keep searching as tons of new free and super cheap options are popping up everywhere. Openrouter even lets you chat with several LLMs at once! Type 1 question once get several answers from different LLMs at once so deepseek and sonnet away.

It's about who you TRUST!

[Hidden]

I have just discovered openrouter 🥳 and while it doesnt have the ultra custom LLMs of huggingface ggufs, it has tons of free opensource LLMs, tons, and a bunch of closed source ones. my new favorite opens are Mistral Small 3 24B and Rogue Rose 103B, Llama 3.3 70B is still my main, you can access Gemini flash 2.0 exp free as well. If hugging chat is lagging behind with 6 LLMs keep searching as tons of new free and super cheap options are popping up everywhere. Openrouter even lets you chat with several LLMs at once! Type 1 question once get several answers from different LLMs at once so deepseek and sonnet away.

Sharing that in the official hugging chat discussion section is wild