The article literally continues by saying that this “close contact” is primarily about avoiding LEO object collisions.
I’m sure these oligarchs are colluding on other shit, but it’s completely disingenuous to try to frame this particular comment as anything other than for operational purposes.
deleted by creator
deleted by creator
It depends on the model. For newer stuff, and Qwen3.8 27b specifically, its Qwen Sparse Attention/Gated DeltaNet architecture does much better than a lot of previous models.
The old rule of thumb was that the middle of the context window can get lost in old models, but Qwen3.8 27b and Qwen 3.8 Flash Next work fine, even when using most of the 262k native tokens of context… but this long context requires 8GiB of VRAM just for the context, and this is with FP8 KV quantization.
I still don’t trust much more than 128k though, and most harnesses automatically compact if a request would exceed a certain threshold (e.g., OpenCode is the higher of 15% of max or 16k tokens for its buffer).
For smaller models 16-32k is probably fine unless you’re using a model that is extremely old, like llama3 or phi 2.5. But you’re going to struggle to get anything other than a simple chatbot with very short conversation on a 4GB card. Maybe light translation or document work, but don’t expect anything useful in coding or agentic work.
deleted by creator
Or, there is an easier explanation:
Research shows that it takes an average of 23 minutes and 15 seconds to regain focus after an interruption.
https://www.researchgate.net/publication/388110139_The_Impact_of_Interruptions
They’re posted on GitHub pretty regularly, here’s one for the 3090/A5000 specifically.
https://github.com/mikecovlee/qwen3.8-27b-24gb-recipe
In particular, I think you want at least the following flags to limit the context length and quantize the Key and Value caches (full context is 16GB alone at full precision KV):
-c 65535 –cache‑type‑k q8_0 --cache‑type‑v q8_0
Using q8_0 for Key and Value cuts that in half. So native full context of 262,144 tokens costs 8 GiB instead of 16, but to fit on one card, something like 65535 would only add 2 GB of VRAM at Q8 KV, respectively. I have also heard good things about using q4_0 for KV, which would cut the context budget by half again, with less than 2% loss.
What software are you using for your inference server (llama.cpp, ollama, vllm, sglang, etc)? There are quite a few published recipes that should get you where you want to go.
Wouldn’t Q4 with FP8 KV cache and full context fit on the 24GB card alone? I’m fairly sure 64K fits, if not, and I’m also really curious about loss rates for some of the newer experimental INT4 KV caches.
What are the consensus Email/Drive and VPN privacy focused replacement options?
Tuta seems legit but no bundled VPN service.