Viewing profile — ljosifov

omp - current top, after using codex claude opencode pi that I still use too

Hear hear. IQ tokens to cheap to meter upon us. So many things changed since last week. Now I've had Prime agent session grinding into its 20-th hour still not giving up. Been usin…

Love pi. It's good to have a minimal agent, always welcome. Even if only to bootstrap install other agents. E.g. recently Hermes stopped installing under Termux (v0.19 - no, v0.18 …

Same. And I have come to use OMP (oh my pi) agent /advisor mode to put a 2nd model on the case (also mid-size one), reading everything. It can not block anything or change anything…

I usually doubt the 'small dataset tuned' variants. B/c ages ago (in the NN prehistory) I've done some NN training, and appreciate how hard it is to improve in general, and how eas…

Hobbled - but not to death, the few times I use it (usually on a plane). I tried 2bit of a 20% REAP reduced experts. :-O That's the biggest that fits on my own h/w (3yrs old M2 Max…

True - they are workhorses. Not super bright, but good enough for lots of everyday tasks. I've found sweet spot to be turning thinking off, as it adds small or no value, while incr…

Running 27B dense model on M5 128GB is ok, but one can do better. On M5 128GB one can make use of the ram and use sparse MoE. For example, DeepSeek-V4-Flash will fit, served by Dwa…

Haha :-) - FoxPro and Clipper next.

Not replaced but supplemented. For off-line coding current setup is pi + ds4-server + DeepSeek-V4-Flash REAP25 (on M2 Max 96gb). For simpler programming related (e.g. text2sql) as …

For high Ram (unified), and relatively middling to lowish Tflops and bandwidth GB/s, usually MoEs are most hopeful. The current top-1 in the (iq, tok/s, @ context depth) ranks for …

Yes, it's performant, and esp performant at non-trivial context depths. DeepSeek-V4 DS4 (and Flash - DS4F) drop tok/s speed much less than the rest. On my M2 Max it took context de…

Thanks for the tear down. IDK anything about quantum (my knowledge there starts and ends with https://www.scottaaronson.com/democritus/lec9.html ), but amused enough to follow in t…

+1 for boring. Boring code is Solid Code, in the sense of "Writing Solid Code" - the old book by Steve Maguire.

Thanks for the DS4, will give it a try. Was hoping maybe I can re-quantise shave few GB... MiniMax-M2.7 Unsloth's UD-IQ2_XXS is down to 65GB - it run albeit too slow to be usable t…

On 96gb I can give up to about 88GB to the GPU with sysctl iogpu.wired_limit_mb=88000, without suffering any ill-effects. When pushed higher I tend to notice e.g. graphic driver er…

Love this, even if can't use it atm (not got the h/w - only 96gb on M2 Max). I get it the general comp/public will find it unusable or worse. Reminds me of how home computers were …

What we see and experience - it's all natural, it's the natural order. :-) When people claim something is un-natural, usually it's natural in that occurs in nature, only - they the…

In the same boat with 7900xtx. 24GB vram, on paper decent performance, in reality most things don't run. Only llama.cpp is consistent that it can run most models, even if maybe not…

~/llama.cpp$ build-.../bin/llama-batched-bench -m models/....gguf -npp 512,1024,2048,4096,8192,16384,32768 -ntg 128 -npl 1 -c 36000 On amd 7900xtx Qwen3.6-27B-Q4_K_M | PP | TG | B …

Glad to see other people using it. Saved my life, was going crazy click-clicking to nab the right window. Now Cmd-1..9 brings to focus a window of my chosen application. (Chrome) I…

Say more please if you can. How/why is ik_llama.cpp faster then mainline, for the 27B dense? I'd like to be able to run 27B dense faster on a 24GB vram gpu, and also on an M2 max.

Everyone should do the calculation for themselves. I too pay for couple of subs. But I'm noticing having an agent work for me 24/7 changes the calculation somewhat. Often not taken…