I tried it. Nothing local or open weights can touch Fable/Opus/Gemini for my use cases.

mapontosevenths a day ago | parent | next [-]

Realistically it can't match Fable, let alone Opus today. It can however beat basically all of the models from 1 year ago. If last years state of the art is "good enough" for you today then local is great.

▲

UncleOxidant 18 hours ago | parent | next [-]

I'd argue that Qwen3.8-Flash-Next is basically at Opus 4.6/4.8 level from about 6 months ago.

	▲	pwython 17 hours ago \| parent [-]
		Maybe at Opus 4.6 level for the "easier" tasks. But honestly if you were given a choice between a computer with Qwen 3.8 or one with even older Sonnet 5, both local, same tok/s, window size, etc... what are you picking?

▲

gwerbin 21 hours ago | parent | prev | next [-]

What open-weight models can match Opus 4.x or GPT 5.4 performance at a reasonable throughput?

▲

UncleOxidant 18 hours ago | parent [-]

Reasonable throughput depends a lot on your hardware. I'm running Qwen3.8-Flash-Next on a 128GB Strix Halo box at 50t/s gen (using the gufo inference engine) and it feels like Opus4.6/4.8 level performance. It's an amazingly good model. I've got it coding a C->microcode compiler in OCaml and it's doing great (there's also verilog code generation involved as well so this is a pretty good stress-test, I think).

▲

mapontosevenths 17 hours ago | parent [-]

Agreed.

Flash Next is really great, but you still need pretty decent hardware. A DGX Spark, Strix Halo, or Mac with a lot of memory. You can use things like Strata to squeeze it into a system with only 32GB of VRAM by offloading a lot of it to system memory and still get something that "works", but the quality falls off a cliff too. At that point you get better results out of Qwen 3.8 27b in int4.

Never go below a four bit quant if you want good results. A worse quant of a bigger model is often easily beaten by the small model at decent quality. A lot of the people who think local AI suck think that because they don't understand that low quants == dumbass model. You aren't just compressing data, you're reducing the amount of compute it uses which effectively lowers it's IQ.

If you want to run something actually useful for cheap Qwen 3.8 27b on a 32GB GPU in int4 should be passable. It's more like Sonnet for a year ago. To match last years Opus you really need at least 128Gb.

Personally I have two Sparks connected with ConnectX 7. Now I can run GLM 5.3 locally at 30-40 tps and it's honestly been great. It really cut my dependence on cloud providers and I can run an abliterated version that never refuses my Cyber related tasks.

▲

tyzoid 16 hours ago | parent [-]

From experience, qwen3.8 27b with gsq/rco at iq3_xxs has good performance with little intelligence loss.

	▲	mapontosevenths 15 hours ago \| parent [-]
		Some of the weird new quants really do push the limits, but at the end of the day that compute you're eliminating is the actual 'work' the model is doing. Folks like to think of 'weights' as just storage, but they aren't (except with stuff like engrams). Those digits of precision encode actual computation, not just storage. There is always a cost, it's lossy compression after all. It's like MP3 vs AAC. If you can't hear the difference it just means you haven't encountered it YET. That's not to say that you ever will. The cost could be in weird far out edge cases, but whatever it once encoded... It's gone now and it ain't coming back.

▲

100111011111 18 hours ago | parent | prev | next [-]

Interesting, mine freezes the whole laptop:-)

▲

appletrotter 18 hours ago | parent | prev [-]

Last year's state was not good enough for me, but this year's state next year would be great

▲

boomskats a day ago | parent | prev | next [-]

What it did you try, and what are your use cases? Genuinely curious.

▲

xeshuman a day ago | parent | prev [-]

I am also curious what exactly you tried. Depending on your hardware it might also be worthwhile to stay in-tune with Qwen 4 and GLM 5.5/6.0 leaks.