Daily Shaarli

All links of one day in a single page.

August 15, 2026

Add Qwen3.8-27B + Muse Glimmer 30B llama.cpp configs (single 3090) by Isaac-opz · Pull Request #992 · noonghunna/club-3090
thumbnail

qwen3.8-27lb decoding at 30-33 tokens/s

  • UD-Q4_K_XL weights
  • Q4 KV cache for both K and V
  • No MTP
  • Text-only, with no vision projector
  • One server slot
  • 262,144 allocated tokens
  • Small microbatch to control activation memory