C
Jul 17, 2026Colibrì: Unleashing Gigantic AI Models on Your Laptop with Pure C Magic!
Quick Summary: 📝 Colibrì is a C-based runtime for large Mixture-of-Experts (MoE) models...
Jul 17, 20263 min read0 reactions0 comments
Back to articles 
Jul 3, 2026
Tag archive
#moe
N
Jul 13, 2026NVIDIA Unveils Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4: A Deployment-Optimized Hybrid MoE LLM
What Changed NVIDIA has introduced Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4, a new large...
Jul 13, 20264 min read0 reactions0 comments
M
Jul 12, 2026Meituan open-sources LongCat-2.0, a trillion-parameter model it says was trained end-to-end on Chinese chips
Meituan released LongCat-2.0, a 1.6-trillion-parameter open-weight (MIT) model that ran anonymously as 'Owl Alpha' for two months and was, the company says, both trained and served entirely on domestic Chinese AI ASICs with no Nvidia GPUs.
Jul 12, 20263 min read0 reactions0 comments
2 TB of Ukrainian Law + DeepSeek V3 860B on GCP: What We'd Get
We have ~1.5 TB of EDRSR with vectors + ~550 GB of registries, legislation, Spanish sources, and EU-Lex running in prod. If we push all of this through an MoE model the size of DeepSeek V3, scaled to 860B on TPU v5p — what comes out? We break down th
Jul 3, 20267 min read0 reactions0 comments
S
Jun 30, 2026Scaling MoE Models with LongCat-2.0: A Deep Dive into 1.6T Parameter Architecture Design
Explore LongCat-2.0's 1.6T parameter MoE architecture and its breakthroughs in scalability, efficiency, and performance for next-gen AI systems.
Jun 30, 20263 min read0 reactions0 comments
W
Jul 6, 2026Why Local LLMs Got Good in 2026: Multi-Token Prediction, Speculative Decoding, and the MoE Efficiency Leap
Why Local LLMs Got Good in 2026: Multi-Token Prediction, Speculative Decoding, and the MoE Efficiency Leap
Jul 6, 20266 min read0 reactions0 comments
K
Jun 30, 2026Kimi K2.7 Code Local Setup 2026: vLLM, SGLang, GGUF
Kimi K2.7 Code Local Setup 2026: vLLM, SGLang, GGUF
Jun 30, 20265 min read0 reactions0 comments
N
Jun 29, 2026NVIDIA Nemotron 3 Ultra for Local AI in 2026: 550B/55B-Active MoE, 1M Context, NVFP4 — Which Consumer GPU Can Actually Run It
NVIDIA Nemotron 3 Ultra for Local AI in 2026: 550B/55B-Active MoE, 1M Context, NVFP4 — Which Consumer GPU Can Actually Run It
Jun 29, 20266 min read0 reactions0 comments
M
Jun 28, 2026MiniMax M3 Local AI Hardware Guide 2026: The 428B Open-Weight Model You (Probably) Can't Run at Home
MiniMax M3 Local AI Hardware Guide 2026: The 428B Open-Weight Model You (Probably) Can't Run at Home
Jun 28, 20266 min read0 reactions0 comments
K
Jun 27, 2026Kimi K2.7 Code for Local AI in 2026: VRAM Requirements, the 1T-Parameter Reality, and Which GPU Crosses Into Usable Speed
Kimi K2.7 Code for Local AI in 2026: VRAM Requirements, the 1T-Parameter Reality, and Which GPU Crosses Into Usable Speed
Jun 27, 20266 min read0 reactions0 comments
M
Jun 27, 2026MiniMax M3 Review 2026: Open-Weight 1M-Context Frontier
MiniMax M3 Review 2026: Open-Weight 1M-Context Frontier
Jun 27, 20265 min read0 reactions0 comments
G
Jun 27, 2026GLM 5.2 for Local AI in 2026: 744B MoE, MIT License, and Why It's Effectively Cloud-Only at Home
GLM 5.2 for Local AI in 2026: 744B MoE, MIT License, and Why It's Effectively Cloud-Only at Home
Jun 27, 20266 min read0 reactions0 comments