# lfm-vl-seat tunables (nh3-ml1). Copy to `.env` on the server.

# llama.cpp CUDA server, pinned by digest: build b11176 (commit f805c57a2),
# published 2026-09-25. Ada sm_89 is in the CUDA build's target set.
LLAMACPP_IMAGE=ghcr.io/ggml-org/llama.cpp@sha256:1f4b9cf58982dd4d7cc497aea31b1a456ca9a3a1f94f527d317d3fdee0d60ab6

VL_PORT=8030
VL_ALIAS=lfm25-vl-3b
VL_MODEL_FILE=LFM2.5-VL-3B-Q5_K_M.gguf
VL_MMPROJ_FILE=mmproj-LFM2.5-VL-3B-Q8_0.gguf

# 2 parallel slots sharing 16k context (8k each): room for a few images plus text.
VL_CTX=16384
VL_PARALLEL=2