Hoping this is real. It's too bad to see the signals from Qwen that they will not be releasing a 35B-A3B for the 3.8 lineup. The MoE architecture makes a huge difference for being able to run these local models on reasonable consumer hardware.

▲ hgoel 23 minutes ago | parent | next [-]

The way it was said made it sound like they had something better than a 35B-A3B coming.

▲ dofm 3 hours ago | parent | prev | next [-]

Quick tests suggest it’s pretty good at reasoning and tool use (keen to search to check its thinking) and it seems to waste much less time thinking, too.

So it feels very fast.

But it does not seem to be better than Qwen 3.6 35B at coding. A bit worse, I think, though I will test it more.

If you have a machine that can fit a 35B model in VRAM, I would suggest testing Muse Glimmer with (from memory)

  Reasoning strength: low

in the system prompt.

Despite being a dense model, this is actually capable of solving code problems faster than the Qwen MoE, despite having only one fifth of the raw token performance.

▲ mirekrusin 3 hours ago | parent | prev | next [-]

Personally I find speculative decoding much better strategy than MoE – performance wise it's there at 90-100 t/s on 2x4090, great intelligence – really great fit.

▲

d4rkp4ttern 3 hours ago | parent | next [-]

A lot of people, including me, don’t want to bother with GPUs, they’d rather run it on their M1-M5 MacBook. For example the 35B-A3B is very usable even on a M1 64GB MacBook.

▲

mirekrusin 2 hours ago | parent [-]

Speculative decoding also works on Mac, 64G is more than what I have, m5 max should handle up to ~40 t/s with optimized setup (and with a lot of vram you can get great wins on concurrency – that harness can take advantage of for single user task as well), but agree memory bandwidth in mac or spark is still too slow, next gen for both will be great hardware to have for sure.

	▲	smcleod an hour ago \| parent [-]
		I get around 70tk/s on the m5 max, with 5bit AWQ / oQ5 slowing only to around 40tk/s at higher context.

▲

c0m47053 2 hours ago | parent | prev [-]

MoE is great on systems that lack the VRAM to host the full model. On my 16GB VRAM system, I can get 100 tok/s with Q4 Qwen 3.6 35b a3b, and 15 tok/s with 27b.

MTP is a trade-off, as it pushes some more of the model off the GPU.

I have managed to get usable quants of Laguna S2 and even DeepSeek V4 flash on this setup.

There is clearly some intelligence loss compared to similar sized dense models, but I feel like it stomps on the 9-12b models I could run fully on GPU

▲ parsimo2010 4 hours ago | parent | prev | next [-]

Honest question/suggestion for the HN audience- Since Qwen released the weights for Qwen3.8 2.4T-A95B and we already have the staring point of Qwen3.6 35B-A3B, couldn't someone distill the bigger model and make a "pseudo" Qwen3.8 35B-A3B? Sure, it wouldn't be an official Qwen release but couldn't someone improve on Qwen 3.6 and get the thing everyone is asking for?

I am calling this a suggestion for the audience because I don't have the will/resources to do this.

▲

WASDx 3 hours ago | parent | next [-]

"Qwen3.8 35B-A3B" and 4B/9B variants are already on huggingface distilled by hobbyists.

▲

halJordan 2 hours ago | parent | prev [-]

Yes, of course. But no one really wants to be the guy actually renting an entire B300.

	▲	boznz 2 hours ago \| parent [-]
		..And there lies the problem.

▲ smcleod an hour ago | parent | prev | next [-]

The smarter 27B is so fast with MTP I've found I really don't need the 35B-A3B. You get around 70tk/s on a M5 Max lowering to around 40tk/s at higher context sizes.

▲

seanmcdirmid an hour ago | parent | next [-]

I've benched 3.8 27B being significantly slower and less quality than 3.6 35B-A4B (both 4-bit quant, MTP, both using turboquant 4-bit served by oMLX), to the point that I'm not even using it right now (on an M3 Max). What's your use case and what did you observe? I might be missing something.

▲

smcleod an hour ago | parent [-]

I believe you mean 35B-A3B, there was no such thing as A4B. I use 27B and other models for software development, and quite a few research or similar agents. I cannot imagine a world where the old 35B-A3B model is smarter / more capable than 3.8 27B - the difference is night and day for coding at least. Where 35B-A3B was fast and felt like a Haiku model, 27B feels like a strong Sonnet when given the right tools. I don't use turbo quant so can't comment on that, but with the A3B model you're using you probably won't get much from using MTP with small MoE models like that.

	▲	xscott 22 minutes ago \| parent [-]
		People over-quantize things, muck with the temperature and other settings based on superstitions or results from models they think are similar. There's lots of ways to make 3.8 27B dumber.

▲

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

I only get ~4 tok/sec on a M1 Pro with MTP.

▲

Muromec an hour ago | parent | prev [-]

Does 27b mean it fits one 32GB GPU?

	▲	smcleod an hour ago \| parent [-]
		It doesn't mean that, but yes it would (with a 5 bit quant).

▲ verdverm 3 hours ago | parent | prev [-]

I'm running qwen3.8 27B dense on reasonable hardware (oem spark)

tbh, I have stopped using MoE in the name of speed, the dense (with more active parameters) makes a real difference in output quality