

Sum Codes
@sumcodes·3 followers·42 content items
Videos from Sum Codes
100B+ Models on 12GB GPU: Strata, Maya & llama.cpp MoE
Local AI: What's the Power Bill?
Mistral Large 4 'Le Chonk' vs Qwen 3.8 Flash Next: Local Hardware?
Qwen 3.8 Flash-Next on local hardware: Strata, SGLang, llama.cpp
Jev, Cactus Needle & Laya: Rise of Decision Models
Local LLM VRAM Budgets: 8, 12, 16, 24 & 32 GB GPUs
OpenAI's Jalapeño Chip: NVIDIA competitor?
Apple M6 & M5 Ultra 512 GB Change Local AI
Muse Glimmer 30B: Meta's Local Coding & AI Agent
AI Model Optimization: Attention, EasyCache & Quantization
Google's Top AI Minds Are Leaving
SpaceX Revenue Jumps 92% in Q2
MiniMax H3: The New #1 AI Video Model?
AI Video GPU Costs: RTX 5090 vs Pro 6000 vs B200
Matt Pocock's grill-me AI Skill Beats Superpowers?





