LongCat-2.5 weights add up to more than its model card says
The LongCat-2.5 weights sum to 1.78 trillion parameters, not 1.6, and the 4-bit repo is 1,336 GB. I added up the files and counted the asterisks.
Notes from a CTO who has to put agents into production. Every post says what I ran, what it cost, and whether I'd use it.
The LongCat-2.5 weights sum to 1.78 trillion parameters, not 1.6, and the 4-bit repo is 1,336 GB. I added up the files and counted the asterisks.
Edge0 145B fits 24GB VRAM, but its own page puts 31 to 38 GiB on host RAM. A local LLM for coding on 24GB VRAM, with the sums checked.
vLLM vs SGLang for an MoE model bigger than your GPU: paged experts run 1.94 times faster than llama.cpp at FP8, 87.7 vs 45.2 tok/s, per the PR's tables.
Who maintains the official MCP servers? I counted five releases: one account wrote 575 of 591 commits. Every number is a curl away.
OpenSSH releases now come faster because AI finds the bugs. I counted the gaps, diffed the 10.6p2 fix and wrote the checks a small team can run today.
Claude Code privacy in practice: the account email sat in the model's context. I pointed opencode and Codex at a request logger and read what they send.
DeepSeek V4 Flash in 56.56 GiB on a CPU, no GPU, says llama-modchip. I redid the size sum, checked the comparison file, and say what it's good for.
My AI team structure for a startup: four seats, who owns the eval, and the numbers from my own pipeline, including what broke.
Local LLM hardware requirements for Ripple-65B, a 65B dense Apache 2.0 model: file sizes, KV cache and a speed ceiling per machine. I did the maths.