211–220 of 848 posts
This is the perfect candidate for just splattering it on your nvme and then reading it off there and into memory. All of these run perfectly fine on simple m4 silicone:
https://github.com/drumih/turbo-fieldfare
Earlier quoted context omitted.
I'd love to understand this more. Are you saying the Qwen team spends their very impressive human and compute resources on publishing these amazing models and then botches the chat template with mundane bugs? Like maybe I just misunderstand what's the hard part but wouldn't you assume that people who can put together an impressive model can also write a proper jinja chat template for it?
Yes yes, oh god yes. They also spread FUD in the form of terrible recommended sampler settings. If you're using llamacpp, turn on top-n-sigma with sigma of 1, turn off top-p/top-k. You'll thank me later.
Earlier quoted context omitted.
> They do not beat opus on real-world usage We have an internal eval that measures performance on tasks for a handful of embedded systems repos for our mmWave radios (mostly Rust, some C for microcontroller stuff). Qwen3.6-27B scores only 4% lower for pass@1, n=250 compared to Opus-4.8. For the labeled dataset, the average PR size they're being measured against is around 1.5k SLOC. This is very much "real-world usage…
How much does it score though? 0% would be 4% less if Opus was at 4%. Unless you mean relative fraction not percentage points - but people usually mean percentage points in such situations.
0% is 4 percentage points (pp) less than 4%.
Any tips on the best approach at running this at an M4 Max 128GB? Token throughput was a bit slow with the last 27B one (MLX), ended up using the A3B variant but if I could get this one to reasonable speed I'd much prefer it.
Unfortunately, that chip just doesn't really have the memory bandwidth to run this (or nearly any) model at acceptable speeds. I have the exact same chip (M4 Max 128GB) and I've been trying to optimize a completely purpose-built implementation with Fable and this is just not possible. Even if you could reach the full 576GB/s, it's just physically impossible to exceed these numbers with the model's architecture: 2 bpw…
Also whats your cutoff for 'acceptable' speed? I would have said 25tok/s.
Earlier quoted context omitted.
just to clarify. yes YOU built it. just because you used some tool doesn't mean the idea, prompting, reprompting, babysitting was not your creative input and effort. put differently, if you put a random person infront of whatever model you used (say, a 50yo receptionist at a pharmacy in india), they would not have been able to create that, because they would have lacked the motivation, idea, background knowledge, tas…
So if I hire an artist and am a motivated individual, have an idea for a painting, have background knowledge about paintings and have taste in paintings and can offer a critique of the painting as the artist paints it, then somehow I created the painting? Absurd logic. The AI built the website.
Earlier quoted context omitted.
4% is within the margin of error anyways for pass@1, so I think pass@k > 1 is gonna be the better indicator of any movement (still need to calibrate the optimal k to re-test). 10 seems too tolerant even though that tends to be the next tranche I reach for.
Depends on where you sit on the binomial curve. At p=0.04 for n=250 4% points would not be within margin of error.
Earlier quoted context omitted.
> They do not beat opus on real-world usage We have an internal eval that measures performance on tasks for a handful of embedded systems repos for our mmWave radios (mostly Rust, some C for microcontroller stuff). Qwen3.6-27B scores only 4% lower for pass@1, n=250 compared to Opus-4.8. For the labeled dataset, the average PR size they're being measured against is around 1.5k SLOC. This is very much "real-world usage…
[flagged]
Earlier quoted context omitted.
> LM Studio doesn't work behind proxies. Woa, is that still a thing? You mean like SOCKS5 stuff that you have to manually configure in every application that uses the internet? I mean maybe I'm just living under a rock but I feel like that's a rather niche situation you got there.
> I feel like that's a rather niche situation you got there Every big company in the world uses a network proxy. LM Studio, as far as I can tell, cannot be configured to work behind such proxies.
Earlier quoted context omitted.
I'm hoping too that they'll put out some MoE variants. Qwen3.5:122b:a10b can run about twice as fast as this 27b dense model. Edit: Like its predecessors, 3.8 seems really inclined to overthinking, and on a 27b dense model that's kind of painful. I think I'm going to stick with gemma4:26b-a3b as my go-to because it runs about 4x as fast and tends to only need a fraction of the tokens in its 'thinking' stage to get th…
Reduce or turn down thinking: https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates
Since it might be helpful to some, here's my current commandline for llama.cpp running on an RTX 4090 with my monitor moved to the iGPU to free up all of its VRAM. llama-server -m Qwen3.8-27B-IQ4_NL.gguf --mmproj mmproj-BF16.gguf -c 170000 --parallel 1 -ngl -1 --cache-type-k q8_0 --cache-type-v q8_0 -b 1024 -ub 512 --flash-attn on --no-context-shift --no-mmproj-offload --spec-type draft-mtp --spec-draft-n-max 5 --spe…
Do you find it useful or worthwhile to split a large LLM across two GPUs on a desktop? If you've tried it, what worked well and what didn't? I'm especially interested in mismatched VRAM setups, e.g. a 16 GB GPU + a 24 GB GPU. How much overhead did you see from inter-GPU transfers, and did the extra usable VRAM outweigh the performance hit?
Llama is decent at auto optimizing it if you let it use both gpus. It’ll split the workload so the contiguous layers are all on one gpu. Once the model is loaded, you only transfer weights between gpus once (per token?), at the layer boundary.
I run on an 8gb 3070 and 12 gb 3060, and the only weird thing is that the weaker card gets more layers (and therefore work) because it has more ram.
Oh, if you’re barely fitting the models into your vram, you may need to explicitly adjust the layer balance between cards — sometimes it fails to realize it should have put certain things (like draft models) on the other card so you can fit one more layer in.