@DedeProGames hows your wallet doing? 🤣
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
He/Him. I like LLM's and VLM's. I work with my other friends to make stuff. We are in year 7 and we are enthusiastic about AI. We are based in Australia 🇦🇺
Recent Activity
new activity about 1 hour ago
Compactbot/model-requests:New model request: SuperSmallJokeClaude repliedto DedeProGames's post about 3 hours ago
how is this possibleOrganizations
replied to DedeProGames's post about 3 hours ago
replied to Banaxi-Tech's post about 3 hours ago
lol we did Italy in like history class for 3 lessons
replied to DedeProGames's post about 9 hours ago
@GGUFGuy i don’t even have a card 😂🤣🤣🤣
reacted to DedeProGames's post with 🤯 about 9 hours ago
Post
3663
how is this possible
- 10 replies
replied to SeaWolf-AI's post about 22 hours ago
@SeaWolf-AI thanks! I will test this on molab as soon as I can!
Stop dropping m*lab lil bro, its called gatekeeping
Oop
replied to SeaWolf-AI's post about 22 hours ago
@SeaWolf-AI you should probably edit the part of the post that says laptop as my laptop disagrees😂
replied to SeaWolf-AI's post 1 day ago
@SeaWolf-AI thanks! I will test this on molab as soon as I can!
reacted to SeaWolf-AI's post with 🤝➕😎👀🤗❤️👍 2 days ago
Post
5887
💻 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: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
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: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
- 27 replies
replied to SeaWolf-AI's post 2 days ago
Or not yet idk
replied to SeaWolf-AI's post 2 days ago
@Banaxi-Tech oh ok. I don’t think anyone uses Em dashes. Like our school don’t even teach them
replied to SeaWolf-AI's post 2 days ago
@SeaWolf-AI I am not too sure if 180B is pocket sized. Would it be possible if you could make a 4-14B version using the same method? That would be easier to test on my laptop
replied to SeaWolf-AI's post 2 days ago
@Banaxi-Tech wdym?
reacted to Banaxi-Tech's post with 🤗❤️ 2 days ago