lm mmap --lazy-mode on -ngl 99 -c 32768 \ mmproj-Qwen3.8-Flash-Next-BF16.gguf --local-dir. llama-mtmd-cli -m IQ3S/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3S-00001-of-00002.gguf \ --mmproj mmproj-Qwen3.8-Flash-Next-BF16.gguf -lm mmap --lazy-mode on \ -md mtp-Qwen3.8-Flash-Next-Q80.gguf --draft-max 4 -lm mmap --lazy-mode on -ngl 99 -lm mmap --lazy-mode on keeps the n-gram table memory-mapped on disk: it is 28.8 GB and one row is read per token. Shard 1 wants to be resident (VRAM or RAM); shard 2 is fine on an SSD. The vision projector is a standard clip GGUF shared with the upstream tiers, 0.91 GB. Native context is 262,144 tokens and the KV cache grows with it, so start at -c 32768 and work…