johnlockejrr/hebrew-targum-vocalized
Viewer ā¢ Updated ā¢ 15.1k ā¢ 45
šļø Building on HF
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a model about 12 hours ago
Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated repliedto DedeProGames's post about 18 hours ago
how is this possible repliedto SeaWolf-AI's post about 18 hours ago
š» 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.
š¦ 360 GB ā 111 GB (4-bit GGUF, 4 files)
š„ļø No GPU: one server CPU (16 threads) at 18.4ā21.0 tokens/s
š» RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
š§ 128 GB mini PC: whole model in memory, no GPU needed
šÆ MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
Ā· Only ~3B of 180B parameters are active per token (10 of 512 experts)
Ā· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
Ā· 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.
š Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
š¤ Model: https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
š§¬ Original: https://huggingface.co/FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoEOrganizations
