Models · family

Small / curated models

Curated sub-10B research checkpoints — Bonsai / SmolLM3 / Nanbeige / Nemotron.

A grab-bag of small research models that don't fit a larger vendor family but earn their place in the registry by being unusually good at something specific — agent reasoning at 1.7B (Bonsai), long-context at 3B (SmolLM3), or pruning-recipe research (Nemotron). See also our notable small models callout for the curated short-list.

family
Small / curated models
aliases
6
lines
4
install
rapid-mlx serve <alias>
OpenAI base URL
http://localhost:8000/v1

Lines in this family

Bonsai · 3 aliases

Research line — 1.7B / 4B / 8B unpacked variants for distillation and draft-model experiments.

parser: hermes

aliashf repotool parserreasoningflags
bonsai-1.7b-unpackedprism-ml/Bonsai-1.7B-unpackedhermesglm4spec
bonsai-4b-unpackedprism-ml/Bonsai-4B-unpackedhermesglm4spec
bonsai-8b-unpackedprism-ml/Bonsai-8B-unpackedhermesglm4spec

Notes & caveats

SmolLM3 · 1 alias

Hugging Face's small-but-mighty 3B — strong sub-4 GB chat model with long-context training.

parser: hermes

aliashf repotool parserreasoningflags
smollm3-3b-4bitmlx-community/SmolLM3-3B-4bithermesqwen3spec

Notes & caveats

Nanbeige · 1 alias

Small instruction-tuned checkpoint kept for research diversity.

parser: hermes

aliashf repotool parserreasoningflags
nanbeige4.1-3b-4bitmlx-community/Nanbeige4.1-3B-4bithermesdeepseek_r1spec

Nemotron · 1 alias

Pruning-research checkpoint with hybrid cache — useful for studying compression-vs-quality trade-offs.

parser: hermes

aliashf repotool parserreasoningflags
nemotron-30b-4bitlmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bithermesqwen3hybrid · moe

Notes & caveats

External reading

Where next