I’m running Qwen3.8 aggressive uncensored Q4_K_M on a 4090 in a loop against the 2026 CrackMe CTF challenges.
Using oh-my-pi in a prebuilt environment that I let Qwen build too.
Codex wouldn’t even look at the files - literally, as soon as it read something with CTF it shut down. Didn’t even offer to fall back to a dumber model.
It’s hot and also LOUD and runs the battery down quick.
But I’m having a lot of luck just running things when I’m away from the computer and can leave it plugged in.
It starts going weird (unreliable and slow) with context over 80k so you have to pick tasks one at a time and baby sit a lot more than Claude. But it really is very capable and feels like there’s an intelligence there to talk to. Maybe gpt-4 level clever?
I have an m5 max 64gb and I think anything slower would be quite painful.
I have an m3 max 64GB and it runs ok, I was playing around with it last night. Its reasoning is better, but the token/s still makes an MoE model (35B A3B) preferable so I switched back.
Try using Goose instead of Claude's harness? Goose doesn't load as much context in at the start, so it might be more usable. I've definitely been able to get it past 128K, although I typically don't go beyond 70-80k. MoE might also be better at this.
My M4 Pro 48GB gets about 13tok/s, in both 3.6 and 3.8 27b Qwens. Qwen A3B and Gemma get closer to 100tok/s from memory but the results are pretty poor for coding tasks.
Edited to add: for agentic workflow I’m running omlx which tells me it has about a 90% cache hit rate (tradeoff is some disk and mem space) - that noticeably changes the felt speed.
I tried it on my M1 MacBook Pro. It's slow but surprisingly smart as a general purpose LLM. Maybe GPT-5.3 level. I gave it a bunch of tools and it can search the internet, make product recommendations, document, code, etc.
What GPU you end up with for that price? Vast.ai (https://cloud.vast.ai/?priceInstanceHourlyMax=2) has a bunch of setups available to reach 192GB VRAM under $2 :) Quick skim showed 4x48, 2x96 and 8x24, all for under 2 buckaroos or around there.
Awesome, I used Claude to write a small python script to do the same with Linode's API. The only difference is I setup a persistent drive, and with Linode you can boot off of it. So my biggest start up lag is ~ 2 minutes to deploy + boot, then maybe 2 more to warm the model.
I actually dislike LLMs. But I'm a realist, and on-demand compute like this is massive cost saving measure.
(persistent drives are relatively cheap, compared to a box with several GPUs.. or even one. I find it worth the expense)
Does it need to respond fast? For important applications, I'm sure we'd all be fine waiting 20 minutes for a high quality, usable answer. Or is it the need for interative refinements that make speed relevant?
It requires patience but it’s more like waiting 5 mins for it to do tasks. You need to be much more involved though and do things slower than Claude where you can trust it to do a lot of tasks at once. It doesn’t have the context for that
People who use Ollama generally (not everyone obviously) don't always clearly understand what quantization they use when running models, so people end up saying "I tried running Qwen 3.8 27b locally and it was dumb" while Ollama would default to a Q4 version of the model, which has very different results from the BF16 weights, doesn't really speak to the model itself because it's been so quantized in that case.
Sure, makes things easier, but tons of people misunderstand what they're using, then base and share their experiences on that, without really specifying what exact weights they use too.
For a single local user, using llama.cpp directly shouldn't be a problem if you're already using Ollama's CLI, it works basically the same except you manage weights yourself, and if you put your favorite agent to make sense of the faux "registry + image layers" Ollama has prepared locally for you, you can reuse the files you've already downloaded with Ollama.
I know nothing about "vLLM" -> anything better compared to "llama.cpp"?
I started with "Ollama" (precompiled version) and it worked and was good enough to understand the very basics.
Then I downloaded the sourcecode of "llama.cpp", compiled it with specific compilation options for my GPUs (CUDA/nVidia using proprietary module on Gentoo Linux) & CPU (AMD), and the same model ran twice as fast -> since then I stuck with "llama.cpp" (and "ik_llama.cpp" in very few cases).
I honestly don't know what made "Ollama" (precompiled) so much slower than "llama.cpp" (compiled locally) at that time and I'm too lazy to doublecheck now, in any case I now absolutely love all the knobs that "llama.cpp" has to tune your hardware setup & your workload, which is the reason why I recommend it.
From what I've heard, Ollama has a bad reputation because it's a thin wrapper around llama.cpp without attributing it properly, thereby stealing recognition from the maintainers doing most of the work
It seems, and that seems is entirely my unvalidated impression, that Ollama lags in features, as they're integrating after the fact those changes. But (seriously) an LLM told me that, when some aspects of MoE models were better supported with the latest llama.
And it did in that case make a significant difference.
It's very far behind llama.cpp, vLLM and SGLang in features yes. In part because of that but also due to some poor default settings it generally performs a lot worse as well.
most of the time when a local model feels dumb its not the quant, its the chat template. a lot of gguf mints just drop the template from the metadata and the runtime silently falls back to chatml. model still talks fine so nobody notices, it just gets noticeably dumber. got burned by this myself serving qwen, now i grep the gguf for the template tokens before i blame anything else. second place is sampling, people run whatever defaults their ui ships instead of what the vendor recommends and then compare that to benchmark numbers that were run greedy or with the official settings
Using oh-my-pi in a prebuilt environment that I let Qwen build too.
Codex wouldn’t even look at the files - literally, as soon as it read something with CTF it shut down. Didn’t even offer to fall back to a dumber model.
But I’m having a lot of luck just running things when I’m away from the computer and can leave it plugged in.
It starts going weird (unreliable and slow) with context over 80k so you have to pick tasks one at a time and baby sit a lot more than Claude. But it really is very capable and feels like there’s an intelligence there to talk to. Maybe gpt-4 level clever?
I have an m5 max 64gb and I think anything slower would be quite painful.
Try using Goose instead of Claude's harness? Goose doesn't load as much context in at the start, so it might be more usable. I've definitely been able to get it past 128K, although I typically don't go beyond 70-80k. MoE might also be better at this.
Edited to add: for agentic workflow I’m running omlx which tells me it has about a 90% cache hit rate (tradeoff is some disk and mem space) - that noticeably changes the felt speed.
- find a free GPU droplet on digital ocean
- fire it up
- pull in a snapshot of the model + extra files/packages etc
- set up a ssh tunnel so that the localhost:8000 routes to the above
Then I just configured OpenCode to use the above and was off to the races.
Works out to be about ~$2/hr all said and done which isn't bad as I only pay when I'm using it (but could get expensive with 24/7 running)
What GPU you end up with for that price? Vast.ai (https://cloud.vast.ai/?priceInstanceHourlyMax=2) has a bunch of setups available to reach 192GB VRAM under $2 :) Quick skim showed 4x48, 2x96 and 8x24, all for under 2 buckaroos or around there.
I actually dislike LLMs. But I'm a realist, and on-demand compute like this is massive cost saving measure.
(persistent drives are relatively cheap, compared to a box with several GPUs.. or even one. I find it worth the expense)
Genuine question : is there something fundamentally wrong with Ollama ?
I use Ollama because it is easy to set up and manage (and also because VLLM is not super Windows friendly).
I thought the main advantage of VLLM was better concurrency management (better batching).
But if the quality of the interference itself is an issue, then maybe I should reconsider my choice.
Sure, makes things easier, but tons of people misunderstand what they're using, then base and share their experiences on that, without really specifying what exact weights they use too.
For a single local user, using llama.cpp directly shouldn't be a problem if you're already using Ollama's CLI, it works basically the same except you manage weights yourself, and if you put your favorite agent to make sense of the faux "registry + image layers" Ollama has prepared locally for you, you can reuse the files you've already downloaded with Ollama.
I started with "Ollama" (precompiled version) and it worked and was good enough to understand the very basics.
Then I downloaded the sourcecode of "llama.cpp", compiled it with specific compilation options for my GPUs (CUDA/nVidia using proprietary module on Gentoo Linux) & CPU (AMD), and the same model ran twice as fast -> since then I stuck with "llama.cpp" (and "ik_llama.cpp" in very few cases).
I honestly don't know what made "Ollama" (precompiled) so much slower than "llama.cpp" (compiled locally) at that time and I'm too lazy to doublecheck now, in any case I now absolutely love all the knobs that "llama.cpp" has to tune your hardware setup & your workload, which is the reason why I recommend it.
And it did in that case make a significant difference.
Yes https://news.ycombinator.com/item?id=47788385
This is the version I want to read :)
I assume it is unpleasant in spite of the math, not because of it?