Hackernews posts about MoE

RSS feed for MoE

91
newStrata: Qwen3.8-Flash-Next (125B Moe) on a 8GB+ Nvidia GPUgithub.com
▲ 5simonpure 6d discuss
92
newStepFun teases Step 5 Preview, a 600B/27B MoE, open weights coming Oct 15twitter.com
▲ 3WavyPeng 13d 💬 1
93
newSSD-Llama: SSD-Native Inference for Trillion-Parameter Moe on a Consumer PCarxiv.org
▲ 3AlmostCosmo79 16d discuss
94
newShow HN: Llama.cpp fork with 2-4x multiGPU speed for MoE models bigger than VRAMgithub.com
▲ 2neuralll 9d 💬 3
95
newI joined the 'anti-chatbox' interface movement, and build Moe because of itmoebot.app
▲ 2yisrael_g 19d 💬 1
96
newShow HN: Moe Routing Atlas – which experts fire in Qwen3.5/3.6 35B-A3Bgslaller.github.io
▲ 2gslaller 5d discuss
97
newXing4.0-29B-A4B: China Telecom's Moe Model Trained on Ascend NPUswww.mindstudio.ai
▲ 2Bluestein 14d discuss
98
newShow HN: I made a tiny MoE/Engram viz toolsw-ml-study.github.io
▲ 2softwarewright 21d discuss
99
newThe Newsroom EP01 – OpenAI Ships GPT-5 to Azure – DeepSeek Open-Sources 236B Moewww.youtube.com
▲ 2LebToki 23d discuss
100
newEmpirical Research on MoE Safety Mechanismsdealign.ai
▲ 2Bluestein 24d discuss
101
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 2ibobev 24d discuss
102
newDense vs. Moe Models: Active Parameters, Throughput, and When to Choose Eachdeveloper.nvidia.com
▲ 1pretext 19d discuss
103
newExtending Raschka's GPT-2: an MoE trained from scratch on an RTX 3090www.gilesthomas.com
▲ 1gpjt 24d discuss
104
newFractal-BLT – Zero-allocation .NET 10 MoE runtime streaming NVMe to GPUgithub.com
▲ 1Ctrl_Alt_Haze 27d discuss
105
newShow HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAMgithub.com
▲ 277volotat 14d 💬 81
106
newAsk HN: What do AI improvements at these labs look like?
▲ 2xyzsparetimexyz 21d discuss
107
newShow HN: Way to divide parameter space in LLM trainingzenodo.org
▲ 1genji970 8d discuss
108
newShow HN: PicoLM v1.0-rc2 ("Yura Kana"). Run an LLM on Digital Unixgithub.com
▲ 1gabucino 11d discuss
109
newReverse engineering my e-scooter and rewriting the firmware in Rustbensimms.moe
▲ 452vinhnx 25d 💬 105
110
newDon't call yourself an artisanal programmerpurplesyringa.moe
▲ 57emschwartz 22d 💬 65
111
newVibe Coding Production Kit – a production workflow for AI coding agentsgithub.com
▲ 9Moeeryani 10d 💬 6
112
newGrieving the Loss of Detailspurplesyringa.moe
▲ 6ibobev 10d discuss
113
newWrite While Learningpurplesyringa.moe
▲ 6dalvrosa 15d discuss
114
newGrieving the Loss of Detailspurplesyringa.moe
▲ 4ibobev 9d 💬 2
115
newWrite While Learningpurplesyringa.moe
▲ 3meetpateltech 16d discuss
116
newSqueezing rust onto more things, this time: Flashlightsbensimms.moe
▲ 3Bluestein 21d discuss
117
newEvergardenevergarden.moe
▲ 3birdculture 23d discuss
118
newWe Spoke with Entrepreneurs Living the "7 Vibe 3" Lifestylecadence.moe
▲ 2xyzsparetimexyz 25d 💬 3
119
newEvergardenevergarden.moe
▲ 2birdculture 13d discuss
120
newReverse engineering my E-Scooter and rewriting it in Rustbensimms.moe
▲ 2nitros 26d discuss