How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
DEV Community
How I Run a 27B Local Agent on a 12GB Laptop GPU: KVMem, Tiered KV, and Honest Long-Context Limits
Most local-LLM advice stops at the weights. Pick a smaller quantized model, fit it in VRAM, done....
0 comments
No comments yet.