ianncity/GLM-5.2-Finance-80000x
Viewer • Updated • 79.1k • 261 • 19
ianncity
ianncity
P(doom) Rejects the premise
AI & ML interests
love hate relationship with ai
Recent Activity
liked a Space 1 day ago
FlameF0X/Tiny-T2I-Leaderboard repliedto SeaWolf-AI's post 9 days ago
💻 Data-center AI, now on a laptop: POCKET-Darwin-180B
We're releasing a 4-bit GGUF build of Darwin-180B-RSI, #1 on seven official Hugging Face leaderboards (self-reported), that runs without a GPU.
📦 360 GB → 111 GB (4-bit GGUF, 4 files)
🖥️ No GPU: one server CPU (16 threads) at 18.4–21.0 tokens/s
💻 RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
🧊 128 GB mini PC: whole model in memory, no GPU needed
🎯 MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
· Only ~3B of 180B parameters are active per token (10 of 512 experts)
· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
· Graft quantization: we took the proven Unsloth UD-Q4_K_XL base build and swapped in only the 300 tensors our RSI training changed (300/300 verified)
Under the hood is Model-level Recursive Self-Improvement. The model solves verifiable problems, keeps only its own solutions that check out as correct, and trains on them. No human-written solutions or reasoning traces.
Built for teams that can't send data to an external cloud (defense, finance, public sector) to run a top-tier model fully offline.
📝 Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
🤗 Model: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: https://huggingface.co/FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE liked a model 12 days ago
ForgeWorks/ForgePlex-M2-9MOrganizations
