Announcement
A llama.cpp v0.7.0 command for 128GB Mac/Spark
A user shares a `llama serve` command specifying Qwen3.8-Flash-Next-GGUF:IQ4_NL, `draft-mtp` and lazy mode.
TLDR
A user shared this llama.cpp v0.7.0 command for 128GB Mac/Spark: llama serve -hf ggml-org/Qwen3.8-Flash-Next-GGUF:IQ4_NL --spec-type draft-mtp --lazy-mode on.
Combined views
1.6K
1 Source, first seen ago
