I need the GLM-5.1 weights now (Any new release please so I can feel less guilty about procrastinating xleaning my office tonight)
@theahmadosman
-
GPU Configuration: Gen4 x8 and NVLinked Pairs
By
–
Mine are all running at gen4 x8 when I had only 8x RTX 3090s in this node they were all running at gen4 x16 Also, each pair in the 14 are NVLinked I am not your crypto cryptobro I do this shit for a living
-
Unified Memory Hardware vs. GPUs for AI Agents
By
–
Unified Memory hardware like – DGX Sparks
– Mac Studios are great for background & periodic agents Any realtime agent (requiring low-latency) demands a GPU -
Qwen 3.5 27B with Hermes Agent is Highly Rated
By
–
Qwen 3.5 27B (Dense) with Hermes Agent is REALLY GOOD
-
Software Stack Crucial for Hardware Adoption, GPU Support Lags
By
–
It’s wild to me that folks still don’t understand this A piece of hardware doesn’t matter if the software stack isn’t there Good luck waiting 5 years for that Intel GPU to be widely supported Even the Blackwell kernels aren’t mature yet and it’s already widely adopted lol x.com/AlexKi1993/sta…
-
Owning Hardware is a Must Due to Open Source Developments
By
–
Oh, they will. They’d have done by now if it wasn’t for opensource. Owning your compute / hardware is a must
-
Elon Musk Endorses Top 26 Papers for Mastering LLMs and Transformers
By
–
BREAKING Elon Musk endorsed my Top 26 Essential Papers for Mastering LLMs and Transformers Implement those and you’ve captured ~90% of the alpha behind modern LLMs. Everything else is garnish. This list bridges the Transformer foundations with the reasoning, MoE, and
-
GPU Chat Progress Discussion on Early Phase Topic
By
–
Still early phases for what you’re talking about, I had Alex jump in and chatted with him on the progress of that yesterday in my GPU Chat with Ahmad space
