20:01
2026-07-25
promptcube3.com
large-language-models
Qwen 27B with 128k Context on 24GB VRAM?
Users report running Qwen 27B with a 128k context window on a single 24GB VRAM card by setting Ollama environment variables OLLAMA_FLASH_ATTENTION=1 and OLLAMA_KV_CACHE_TYPE=q4_0, which quantizes the …