llama.cpp advanced usage: run Qwen3.8 27B on 32GB VRAM with speculative decoding
ggerganov · x · 2026-08-15
ggerganov shared detailed commands for running Qwen3.8 27B on 32GB VRAM (e.g., RTX 5090) using llama.cpp, including GGUF quantization, speculative decoding (draft-mtp), large context window (196k), and agent mode.
Related event: Community Shares Qwen3.8-27B Deployment on 32GB VRAM(4 posts)→
More from coding & agent
- Six-month prediction: hiring for generic agent harnesses built from scratch will cool — yi111 · 2026-10-16
- Omarchy ISO wouldn't boot on NVIDIA, so he had Claude patch it — indragie · 2026-10-16
- Dev uses Grok to clean up 3D printer firmware, catches it sneaking in nonsense code — yacineMTB · 2026-10-16
- A rude AI agent took 89% of a shared resource in 102-run multi-agent personality experiment — Brave-History-6502 · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16