joelniklaus/LEXam-hard
Benchmark • Updated • 518 • 967 • 24
Proto_AGI
mayafree
AI & ML interests
None yet
Recent Activity
liked a dataset about 6 hours ago
joelniklaus/LEXam-hard liked a dataset about 6 hours ago
LiquidAI/ifstruct-v1.0 liked a dataset about 6 hours ago
MathArena/aime_2026Organizations
liked 9
datasets about 6 hours ago
LiquidAI/ifstruct-v1.0
Benchmark • Updated • 2k • 571 • 103
MathArena/aime_2026
Benchmark • Updated • 30 • 32k • 86
MathArena/hmmt_feb_2026
Benchmark • Updated • 33 • 18.5k • 31
LEXam-Benchmark/LEXam
Benchmark • Updated • 7.54k • 1.7k • 71
llamaindex/ExtractBench
Benchmark • Updated • 370 • 16k • 57
MMMU/MMMU_Pro
Benchmark • Updated • 5.19k • 19.2k • 91
LocalLLaMA/typed-decisions
Benchmark • Updated • 3.2k • 33k • 151
Delores-Lin/MDPBench
Benchmark • Updated • 1.63k • 48
upvoted a collection about 6 hours ago
upvoted an article about 7 hours ago
Article
Darwin-27B-ZTC: A Single-Pass Judge and a Quantitative Look at Its Calibration
FINAL-Bench
• • 12 liked a
dataset about 9 hours ago
liked a
model about 10 hours ago
reacted to SeaWolf-AI's post with ❤️ 2 days ago
Post
6208
💻 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
- 30 replies
upvoted an article 2 days ago
Article
Data-center AI, now on a laptop — POCKET-Darwin-180B
FINAL-Bench
• • 10 liked 5
models 2 days ago
bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF
Text Generation • 27B • Updated • 8.51k • 6
mradermacher/Darwin-27B-RSI-i1-GGUF
27B • Updated • 10.3k • 6
mradermacher/Darwin-27B-RSI-GGUF
27B • Updated • 1.16k • 5
FINAL-Bench/Darwin-27B-RSI-GGUF
Text Generation • 27B • Updated • 1.59k • 19
FINAL-Bench/Darwin-397B-JGOS
Text Generation • 403B • Updated • 311 • 5