Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
š¤
Open to Collab
2.1
TFLOPS
The Supreme GGUF-SafeTensors Guy
GGUFGuy
122
16
41
Follow
cmjskp5's profile picture
mohkarage-7's profile picture
hardhant's profile picture
49 followers
Ā·
164 following
AI & ML interests
I like llms
Recent Activity
new
activity
about 4 hours ago
Compactbot/model-requests:
New model request: ram-18m
replied
to
DedeProGames
's
post
1 day ago
how is this possible
replied
to
SeaWolf-AI
's
post
1 day 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 𧬠Original: https://huggingface.co/FINAL-Bench/Darwin-180B-RSI #Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
View all activity
Organizations
GGUFGuy
's models
19
Sort:Ā Recently updated
GGUFGuy/hyperdex-trainer
Updated
3 days ago
GGUFGuy/use-novi-the-assistant
Updated
12 days ago
GGUFGuy/cvb
6.95M
ā¢
Updated
13 days ago
GGUFGuy/Kiyo-135M-0960-Q8_0-GGUF
Text Generation
ā¢
0.1B
ā¢
Updated
19 days ago
ā¢
87
GGUFGuy/useless-parameters
Text Generation
ā¢
0.1B
ā¢
Updated
21 days ago
ā¢
41
ā¢
1
GGUFGuy/nanodex-100k-1m
Text Generation
ā¢
100k
ā¢
Updated
22 days ago
ā¢
39
GGUFGuy/hyperdex-most-undertrained-slm
Text Generation
ā¢
50M
ā¢
Updated
22 days ago
ā¢
46
GGUFGuy/nanodex-500k-200m
Text Generation
ā¢
492k
ā¢
Updated
22 days ago
ā¢
77
ā¢
1
GGUFGuy/hyperdex-test
Text Generation
ā¢
1M
ā¢
Updated
22 days ago
ā¢
39
GGUFGuy/xet-test
Updated
24 days ago
GGUFGuy/Glint-2-GGUF
1.06M
ā¢
Updated
26 days ago
ā¢
116
ā¢
1
GGUFGuy/Tiny9
Updated
28 days ago
ā¢
1
GGUFGuy/floppyx3-MEGAmodel-merged-GGUF
Text Generation
ā¢
1.09M
ā¢
Updated
29 days ago
ā¢
116
GGUFGuy/floppyx3-MEGAmodel-base-GGUF
Text Generation
ā¢
1.09M
ā¢
Updated
29 days ago
ā¢
132
GGUFGuy/roblox-blocky-or-style
Text-to-Image
ā¢
Updated
Aug 24
ā¢
22
GGUFGuy/hgbn
Image-Text-to-Text
ā¢
Updated
Aug 20
GGUFGuy/the-largest-model-ever-on-hf
Updated
Jul 23
ā¢
95
ā¢
1
GGUFGuy/parameter-overflow
Updated
Jul 23
ā¢
7
GGUFGuy/GGUF-Pack
2B
ā¢
Updated
May 25
ā¢
608
ā¢
1