The old DeepSeek V4.1 Flash has been my workhorse model for the past month (after running tests comparing w/ Qwen 3.8 Flash Next, GLM 5.3 Flash, MiMo 2.6 Flash (including the MOPD fix)) and I've run tens of billions of tokens through it and pushed it fairly hard in both private internal benchmarking and in my own workloads to figure out where it's strong/weak.

Partly because I run it on very fast local infra (200+ tok/s) and partly because I'm guaranteed it's not being changed on me, I've generally preferred it over proprietary subscription models for daily tasks, as it seems about as capable at mid-level tasks (I reserve Astra/Opus mostly for planning/review).

I've replaced the previous model with 1017, and while it's early, a few observations:

- It's CoT has changed dramatically. I find the heavy Astra distillation claims to be plausible

- It has strong benchmarks scores, and from what I've seen online it's much better at 3D games and such, but that's not so relevant for my work. On my internal evals it is more token efficient, but it actually doesn't score any higher than the previous model

- It's only been a couple days, but it does seem a bit more focused and reliable. DS4 0731 and DS4.1 have been a bit sloppy (as in not-careful, although they did tend to fall into Claudisms as well), and 1017 seems to be a bit sharper.

- I'm running it through some more challenging work, but I'm not sure if it's really at GLM-5.3 level, especially for cyber/RE/hardware poking, which GLM has excelled at.

▲

kbr- 5 hours ago | parent | next [-]

200+ tok/s on local infra? That's crazy. How much did you pay for your hardware?

▲

crossroadsguy 4 hours ago | parent | next [-]

I find these local infra costs crazy heavy duty. I always assume these folks are getting their values worth or that infra is serving multiple people's requests at and justifying the cost. Like I once thought of buying a 48-64 GB RAM laptop (not even clsoe to what these models need) and I realised the equivalent cost will serve me for years of ≈ $30 per month API/sub access. So I assume the usage is also heavy duty, or if nothing then for privacy and safety and then I guess the price, if one can pay, will totally be worth it.

▲

origini 2 hours ago | parent | next [-]

You just need to imagine someone making big bucks in tech + being a little bit money ignorant, having a big house and a nice basement and cheap energy prices.

Than it just makes sense that they already do this.

But to be fair, if i move, enough space for battery, solar and a basement which can take proper ML hardware + heat exchanger, is in my future vision.

▲

mrheosuper 4 hours ago | parent | prev | next [-]

> I realised the equivalent cost will serve me for years of ≈ $30 per month API/sub access

The advantage is no more 5-hours or weekly session limit anymore. Also no chance your proprietary code ends up in someone repo.

▲

amunozo 2 hours ago | parent | next [-]

I still think only privacy is relevant to run on your own infra, never cost.

	▲	vizzah 5 minutes ago \| parent [-]
		near.ai tries to solve this

▲

crossroadsguy 2 hours ago | parent | prev | next [-]

That is literally my next sentence :D

▲

david-gpu 2 hours ago | parent | prev [-]

> The advantage is no more 5-hours or weekly session limit anymore

That is not a concern with pay-as-you-go models like DeepSeek. It is stupid inexpensive.

▲

lnenad an hour ago | parent | prev [-]

If the only variable is money, local models will never make any sense at these prices of infra/subscriptions.

For a lot of people, there are other variables though.

▲

swiftcoder 4 hours ago | parent | prev [-]

This has to be a distilled model? I don't see any route to 200 tokens/s without serious datacenter hardware

▲

naraic0o 3 hours ago | parent [-]

you mean quantized? it’s only got 16B active parameters so it can be pretty fast at decode.

	▲	swiftcoder 2 hours ago \| parent [-]
		sorry, yes, quantised

▲

MayeulC 5 hours ago | parent | prev | next [-]

CoT = Chain of Thought (I had to look it up)

Thanks for the insights. If you edit your post to include the definition, I'll delete mine.

▲

dgellow 3 hours ago | parent | prev [-]

> because I'm guaranteed it's not being changed on me

This is something underrated. With an open weight model I can evaluate the performance for my use case, and know for a fact the model will stay the same over time. No arbitrary “model welfare” rules being introduced later on, no undocumented change to capabilities or performance