I am so excited for Qwen 3.8 27B. It’s a shame how slow prefill (~3-400) is on a strix halo but it’s such a good model for agentic tasks.

▲

colingauvin an hour ago | parent | next [-]

Prefill is survivable if you cache well. But what kills me is the context. Qwen 27 needs a ton of room for KV Cache. I guess not an issue on a 128 GB Halo or Spark, but if you are running of consumer/prosumer GPUs it's miserable to be compacting every 120k tokens.

▲

tarr11 an hour ago | parent | prev | next [-]

What type of agentic tasks are you using it for (eg how complex)?

	▲	syntaxing 9 minutes ago \| parent [-]
		For personal stuff, I use it with AnythingLLM. It replaced any Google search for me. For coding, I run opencode though I have been debating switching to Pi. I would argue it’s at Sonnet 3 level.

▲

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

I find that 35B-A3B is much easier to run on my M4 Max (both prefill and generation)

	▲	markasoftware an hour ago \| parent [-]
		It's well known 35b is much faster (on any hardware) and quite a bit dumber

▲

CamperBob2 an hour ago | parent | prev [-]

How are you running it on a Strix Halo? The weights aren't out yet, are they?

	▲	13rac1 an hour ago \| parent \| next [-]
		I interpret @syntaxing as meaning they are looking forward to running Qwen3.8-27B, but are frustrated by prefill times with other models, such as Qwen3.6-27B.
	▲	syntaxing an hour ago \| parent \| prev [-]
		I meant Qwen3.6. Unsloth supposedly has early preview of the model and the VRAM requirement is the same so most people expect similar model size and type.