aifeifei798/Myriad-MoE-25K-Micro-Experts
Text Generation ā¢ Updated
šļø Building on HF
aifeifei
aifeifei798
AI & ML interests
roleplay
Recent Activity
updated a model about 5 hours ago
aifeifei798/Myriad-MoE-25K-Micro-Experts new activity about 11 hours ago
aifeifei798/Gemma-4-31B-Cognitive-Unshackled:Inquiry regarding ablation efficacy and distributional shift metrics liked a model 2 days ago
Viggle/Qwen-Image-2.1-viggle-turboOrganizations
updated a
model about 5 hours ago
Inquiry regarding ablation efficacy and distributional shift metrics
š 1
4
#1 opened 6 months ago
by 
CosmossG
liked a
model 2 days ago
reacted to SeaWolf-AI's post with š 2 days ago
Post
6009
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: FINAL-Bench/POCKET-Darwin-180B-GGUF
š§¬ 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.
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: FINAL-Bench/POCKET-Darwin-180B-GGUF
š§¬ Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
- 30 replies
liked 2
models 3 days ago
updated a
model 3 days ago
published a
model 3 days ago
published a
model 4 days ago
updated 4
models 5 days ago
published 2
models 6 days ago
published a
model 7 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
liked a
dataset 7 days ago
published a
model 7 days ago