Mosh Ontong

[Mosh Ontong @mosh_Ontong]

@ZixuanLi_ zhipu must have a lite version like the gemini have gemma

[Mosh Ontong @mosh_Ontong]

Or the 1million context set will consume the usage more? I need more clarify on this @ollama

[Mosh Ontong @mosh_Ontong]

@ollama if I set max the glm in the Opencode does it also consume the usage more?

[Mosh Ontong @mosh_Ontong]

@ollama @parthsareen love u ollama. I feel the improvement of your services since day 1. Now I am now in max plan to support you.

[Mosh Ontong @mosh_Ontong]

@Hesamation Yeah, I agree with that. No need to beat those closed model. As long as those open source can work on my tasks HAHA.

[Mosh Ontong @mosh_Ontong]

@ollama @jonoringer curious can I use ollama with zcode or kimi code cli?

[Mosh Ontong @mosh_Ontong]

@Zai_org GLM is good but it doesnt have the multimodal support. And for me it useless. I really like KIMI for now. Hoping, zhipu will release for the multimodal type.

[Mosh Ontong @mosh_Ontong]

@Kimi_Moonshot @ollama yehey?

[Mosh Ontong @mosh_Ontong]

@suni_code This is an anonymous function who’s trying to invoke this inline?

[Mosh Ontong @mosh_Ontong]

@loktar00 @Alibaba_Qwen @Alibaba_Qwen and @Kimi_Moonshot waiting

[Mosh Ontong @mosh_Ontong]

I just tried Mimo using opencode, and yeah it's great and it also a multimodal. Hmmmm, why @ollama dont have this? https://t.co/x5v9tO2EM7

[Mosh Ontong @mosh_Ontong]

@ollama See it stopped the conversation

[Mosh Ontong @mosh_Ontong]

@ollama kindly fix the deepseep 4-fast please. Yet it getting fast but it getting dumb. "DSML" cause stopped the conversation.

[Mosh Ontong @mosh_Ontong]

@LottoLabs @StepFun_ai @ollama

[Mosh Ontong @mosh_Ontong]

Hey @ollama , between my Max and Pro accounts, I’m paying $120/month, but my limits are being eaten up instantly by DeepSeek. It looks like the usage metrics were unfortunately modified recently, as the limits feel significantly lower than before.

[Mosh Ontong @mosh_Ontong]

@a6ni @ollama https://t.co/4I1lgSfcTn this is understandable due to the lack of capacity they need money to buy expensive gpu

[ollama @ollama]

@PhantomByteAI @Alberto8793 we will introduce additional usage in the future -- for now, it's all about getting enough capacity to serve well!

Apologies across the board on the GPU shortages we are having!

[Mosh Ontong @mosh_Ontong]

hoping for the consistency @ollama

[Mosh Ontong @mosh_Ontong]

i love the speed of GLM 5.1 and Kimi 2.6 in @ollama — I am now in Max plan and it’s worth it.

[Mosh Ontong @mosh_Ontong]

@parthsareen ollama dont suppoer claude code desktop anymore and I think this one soon?

[Mosh Ontong @mosh_Ontong]

is @ollama 20 usd usage getting shorten?