yeah, they are as soon as you use a non-mainstream browser. never got past cloudflare with the Pale Moon browser, for instance. seeing a site like reclaimthenet - fighting for a free internet - gated behind cloudflare struck me as odd, to say the least. i just had to prove that i'm not a bot to be able to read the article.
these LFM 2.5 models are crazy fast. the (biggest in series) 8B-A1B model produces 35-40 t/s on an aged 6-core CPU using llama.cpp. it's my go-to model for whenever i need fast local inference. it's also pretty good at toolcalling. would love to see more finetunes on HF, but it appears not many people discovered it yet.
probably more interesting (from 01/2026) https://arxiv.org/pdf/2511.10643 "Black-Box On-Policy Distillation of Large Language Models". they got a qwen 2.5 14B model trained to GPT5 level using the described technique "Generative Adversarial Distillation (GAD)".
there's also the factor of display technology. when i got a new laptop with LED-driven display, i couldn't even look at it longer than 5 mins without getting watery eyes. switched back to the vista-era laptop only because of its 1280x800 TFT display - zero issues with that.
i tried the Q4_K_M model form unsloth with your Q4_K_M drafter, but the required memory to load everything is 72GB. odd. otoh i could load Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled.IQ4_XS.gguf and it requires just ~18 GB:
llama_print_timings: sample time = 45.28 ms / 404 runs ( 0.11 ms per token, 8921.67 tokens per second)
llama_print_timings: prompt eval time = 949.42 ms / 51 tokens ( 18.62 ms per token, 53.72 tokens per second)
llama_print_timings: eval time = 24067.08 ms / 400 runs ( 60.17 ms per token, 16.62 tokens per second)
llama_print_timings: total time = 242192.55 ms / 451 tokens
so i wonder why the params used by the quantified qwen model use way less memory than the ones of gemma.
how ironic that a site called "reclaim the net" cowers behind The Great Clownflare Firewall, which blocks any alternative browsers (like palemoon) and anyone using a proxy. so i can't even read what they have to say.
bleh. i hate how everything gets rustified and more and more critical infrastructure is at the whims of the rust corporation. as a reminder, rust is a language without a spec, without a clear bootstrapping path (one has to trust binaries provided by them), and a history of breaking changes with almost every minor release. getting a rust compiler built from scratch on a new OS/Arch like the author's serenityOS is an almost impossible task.
i had high hopes for ladybird to become an alternative browser anyone with a working C++ compiler could build on whatever platform.
maybe the best and simplest solution would be to not remove gtk2 from debian. the last release is stable and there's no technical reason to remove it (as it still works and compiles just fine), only political ones.