# ==============================================================================
# SmolLM3 3B-it Q4_K_M — HuggingFace (2025)
# Architecture: Decoder-only transformer, GQA + NoPE (3:1 ratio)
#   - 3B params, 11.2T training tokens
#   - 64K native context (128K with YaRN)
# Model size: ~1.9 GB Q4_K_M  |  Full GPU fit (ngl=99)
# Features: thinking mode (/think /no_think), tool calling, 6 languages,
#           Apache 2.0. AIME 2025: 36.7% in think mode.
#
# Download:
#   huggingface-cli download bartowski/HuggingFaceTB_SmolLM3-3B-GGUF \
#     HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf --local-dir ./models/
#
# NOTE: Verify exact filename after download:
#       ls models/SmolLM3* models/HuggingFaceTB_SmolLM3*
# ==============================================================================

MODEL_FILE=HuggingFaceTB_SmolLM3-3B-Q4_K_M.gguf

# All layers fit comfortably — ~1.9 GB leaves ~1.8 GB free for KV + compute
N_GPU_LAYERS=99

# Benchmarked 2026-05-05 on GTX 1650 Ti (3717 MiB):
# Max ctx=24576 (32K OOM). Baseline: 249 pp / 56.8 tg t/s.
# At 24K ctx with fa=1: 260 pp / 58.3 tg t/s (+2%).
# Model context limit = 65536, VRAM is the constraint here.
CTX_SIZE=24576

THREADS=6
THREADS_BATCH=6

BATCH_SIZE=512
UBATCH_SIZE=256

CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0

# 2 parallel slots — less headroom at 24K ctx vs original 16K estimate
PARALLEL=2

# fa=1 gives small but consistent improvement (+2 tg t/s)
EXTRA_ARGS=--flash-attn on --mmap