Entries matching “rtx-4090”

Alok

@analogalok

Muse Glimmer, A 30B parameter dense model swallowing a 130,000 token context window using only 19.3 GB of VRAM (extreme efficiency). No KV cache quantization required. I just benched the new Muse Glimmer 30B (dense) on a single RTX 4090. We are pulling 3,100+ t/s prefill and 75

Agent Workflow Lab runs the Q8 GGUF of Muse Glimmer 30B through llama.cpp on an RTX 4090 plus 3x RTX 3090, measures DFlash speedups and a 120K-token retrieval probe, then has it build a Three.js browser FPS with no human edits.

A 4-byte GGUF header edit that raises Muse Glimmer 30B's 131,072 context limit to 262K. The author shows YaRN scaling only adds prefill cost on this architecture, and verified 262K with 8 slots on one RTX 4090.