Any 'vibe check' on these; I don't have benchmarks but I tried out Le Chonk for general coding work that they claim it works really well at and I was very disappointed, it seemed to make all kinds of obvious errors of the kind that I haven't seen from opus, sol, deepseek flash etc in over a year

▲

maelito 7 hours ago | parent [-]

Just tested Mistral 4 too in Vibe and it's slow. It works well, but is way too slow. Switched back to Mistral's GLM5.3, which is awesome.

Edit : working with GLM5.3 now, it's also slow. Maybe Mistral's under heavy load.

Disclaimer : Not Cofounder of The Forecasting Company here

▲

sspiff 7 hours ago | parent | next [-]

I've been using Mistral Large 4 and some of my other friends have as well.

Something is going on with the performance (as in speed of the service, not quality). Some days it's quite fast, some days it's so slow I interrupt it because I thought it was hanging.

I think they're shifting hosting capacity around, or otherwise messing with the model. Note that it's still a "preview" version, meaning they're still training it further for the final release and they are likely still figuring out the optimal hosting configuration as well.

It wouldn't surprise me to see further changes in both quality of the model and speed before the final release.

	▲	isidor_nikolic an hour ago \| parent [-]
		We are improving all layers of the stack (model, inference, harness) so do expect improvements in quality in perf over the following weeks. <mistral vibe pm here>

▲

pims 6 hours ago | parent | prev [-]

How are you accessing Mistral 4 from Vibe? The only ones available on my end are Medium 3.5 and GLM-5.3 despite having a Pro subscription.

▲

data-ottawa an hour ago | parent | next [-]

I updated my vibe config to point to Mistral 4 and it charges my subscription capacity, not my API allowance. So it is included in subscriptions, you just need to do a little bit of legwork.

▲

isidor_nikolic an hour ago | parent | prev | next [-]

We are rolling it out via A/B experiments and improving the experience as we roll-out. 100% of the users should see it in the following 7 days.

▲

maelito 4 hours ago | parent | prev [-]

Location based maybe ? I'm in France.

▲

pims 3 hours ago | parent | next [-]

Odd, I am in France too. Progressive rollout maybe? I find it weird to announce a model with fanfare but not make it immediately available to customers, let alone paid ones.

	▲	isidor_nikolic an hour ago \| parent [-]
		Thanks for feedback. With future model releases we will aim to have it available to all paid users on day one.

▲

nozzlegear 4 hours ago | parent | prev [-]

I've been using Mistral 4 as well, but from OMP with a Vibe subscription. Not location-based, I'm in the US.

I agree with you though. It's slow as hell, and so is their GLM offering.

▲

maelito 3 hours ago | parent [-]

The GLM offering in the last months was blazingly fast for me.

▲

nozzlegear 3 hours ago | parent [-]

It was for me too, and it's only become slow very recently. I can't say with certainty, but I think it was around the time Mistral 4 launched that it seemed to slow down.

	▲	maelito 3 hours ago \| parent [-]
		Maybe their Mistral 4 usage spiked with the news.