The reason for running those insanely low quants is to fit in extremely limited memory budgets. The first thing you sacrifice is speed, then context and accuracy (up to you in which order). IQ2_XXS and below is desperate/proof of concept territory. If you have a spare half gig for the MTP drafter, run a larger quant instead, it will be less incoherent, and damn the speed, it won't be garbage at least. Only around Q4 I'd allocate the comparative luxury of more memory for a speed increase. At least on a dense model. MTP makes a lot more sense (but helps statistically a bit less) on an MoE.

Qwaiting for that 3.8-35B-A3B

you can still have it, no?

> We also removed the MTP module from smaller quants under UD-Q2_K_XL (8.37GB and lower) to converse around 500MB of disk space - you can use the Q4_0 MTP separate module if needed

I tested Qwen 3.8 on the Blade CTF last night, it took 3 hours but got the correct answer.

I know that didn’t answer your question but I was looking for a test suite and couldn’t find anything.

After reading the logs, there is far less doom looping than with 3.6, but whether that’s a one off or not is up for debate.

Q4_K_P

Unsloth use a property dataset they don't release, however you can indeed create quantisation locally on your machine and it's pretty easy, llama.cpp comes with everything you need.

Not 1-bit, but I’m getting pretty good results with some light coding using unsloth’s previous 2-bit quant of qwen3.8-27b. With these new quants i may be able to bump up to 3bit, tho it’s already running so slow (15tok/s average for the first 32k of context) that the speed hit might make it not worth the extra smarts

Yes, and if you have the PCIe lanes (say, an x16 lane - actually delivering 16 lanes! - to each GPU) it's also quite performant - it's called a tensor split in llama-server.

If your motherboard/cpu doesn't actually have those (few do outside some xeons, epycs and threadrippers) you can still do it - it's called a layer split and will work even with 1 lane per GPU. Each GPU will work at its maximum speed, but only 1 will be active at any given instant - imagine a relay race.

(Didn't mention which PCIe generation - obviously the higher the better. At v4 and up, even 8 lanes per GPU would be enough for a performant tensor 4-way split)

Edit: If you have more than 1 user at a time, the GPU can actually all be working all the time, if there are enough parallel requests to serve. But you need enough KV cache for all the sessions you're running in parallel.

I do use 2 amd gpus and I get high 40 for generation, 500 for pp and low 20/100 by the end of the context of 256k.

llama-server --host 0.0.0.0 --port 8089 -m Qwen3.8-27B-UD-Q8_u.gguf --spec-type draft-mtp,ngram-mod --spec-draft-n-max 3 --spec-draft-n-min 1

if you have an igpu and want to exclude or just use some gpus you can use

--device Vulkan3,Vulkan2,Vulkan1

in my case vulkan because of amd, you can see your devices with

llama-server2 --list-devices

Available devices: Vulkan0: AMD Radeon Graphics (RADV RAPHAEL_MENDOCINO) (33515 MiB, 29349 MiB free) Vulkan1: AMD Radeon RX 7900 XTX (RADV NAVI31) (24560 MiB, 4911 MiB free) Vulkan2: AMD Radeon RX 7900 XTX (RADV NAVI31) (24560 MiB, 7681 MiB free)

I am getting 14 t/s on my 16 GB card at full context with the UD-Q3_K_XL quant. Model link: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF.

Of course. Models don't actually require VRAM. Nor do they require regular RAM. You could have 1 GB of RAM and swap the model to disk as you need different parts of it. And if you didn't have enough disks you could access weights via a network connection.

Yes, but unless they support NVLink (they don't), it's quite slow.

What size context are you able to squeeze in with less than 2gb of headroom? I have had some luck using a quantized kv cache but i fear that also decreases overall quality.

What about do you mean by single threaded? Each token is predicted by using parallel computation on the GPU.

I don't think you can extrapolate that measurement across multiple sequential draws like that. We presumably are comparing against a single trajectory rather than a tree of trajectories. So once we make the wrong choice and step off of the blessed path, we have no way to assign a ranking to the next token; it's error is undefined.

I've seen LLMs self correct in chains of thought ("because of foo and bar, I need to... Wait, bar is not true, so that won't work") so I have to imagine this is a massive overestimate, errors do not necessarily compound.

That's not how that works. Selecting a different token is not inherently erroneous. A correct solution can still be found despite divergence.