# Ollama Modelfile for Nex-N2-mini-IQ3_XXS.
# Requires Ollama 0.19 or newer (qwen35moe arch landed in llama.cpp PR #19468 on 2026-02-10).
#
# Usage:
#   ollama create nex-n2-mini -f Modelfile
#   ollama run nex-n2-mini "your prompt"

FROM ./Nex-N2-mini-IQ3_XXS.gguf

# Context window (4096 default; bump up to 262144 if you have GPU memory)
PARAMETER num_ctx 4096

# Offload everything to GPU. Drop if you have less than ~14 GB GPU memory.
PARAMETER num_gpu 999

# Leave 2 cores for the desktop on a typical 8-core laptop.
PARAMETER num_thread 6

# Single-user laptop: don't allocate multiple parallel KV caches.
PARAMETER num_predict -1

# Pin the model in RAM after first load (avoids re-mmap on each request).
PARAMETER use_mlock true

# Sampling defaults that match the model's training (Qwen 3.5 family).
PARAMETER temperature 0.4
PARAMETER top_p 0.95
PARAMETER top_k 64

# ChatML stop tokens (Nex-N2-mini uses Qwen 3.5 chat format).
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|im_start|>"