Small / curated models
Curated sub-10B research checkpoints — Bonsai / MiniCPM5 / 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 — ternary-weight agent reasoning (Bonsai), 1B on-device chat (MiniCPM5), 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
- 8
- lines
- 5
- install
- rapid-mlx serve <alias>
- OpenAI base URL
- http://localhost:8000/v1
Lines in this family
- Bonsai (ternary) (2 aliases)
- MiniCPM5 (2 aliases)
- SmolLM3 (1 alias)
- Nanbeige (1 alias)
- Nemotron (2 aliases)
Bonsai (ternary) · 2 aliases
Ternary-weight research line — 2-bit packed 1.7B and 27B checkpoints, tool-call capable via the hermes envelope. Tiny footprint (~2.5 GB at 1.7B), useful for agent and draft-model experiments.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| bonsai-1.7b-2bit | prism-ml/Ternary-Bonsai-1.7B-mlx-2bit | hermes | — | — |
| bonsai-27b-2bit | prism-ml/Ternary-Bonsai-27B-mlx-2bit | hermes | qwen3 | — |
Notes & caveats
- Ternary 2-bit weights — the 1.7B lands around 2.5 GB on disk yet still passes tool-call formatting.
- The 27B ternary variant adds a
qwen3reasoning parser for<think>-style traces.
MiniCPM5 · 2 aliases
OpenBMB's on-device 1B — strong sub-1 GB chat/agent model with a minicpm tool-call envelope and qwen3 reasoning. Ships a stock 4-bit and an OptiQ 4-bit quant.
parser: minicpm
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| minicpm5-1b-4bit | openbmb/MiniCPM5-1B-MLX | minicpm | qwen3 | — |
| minicpm5-1b-optiq-4bit | mlx-community/MiniCPM5-1B-OptiQ-4bit | minicpm | qwen3 | — |
Notes & caveats
- 1B footprint — the smallest tool-call-capable text model in the registry.
- OptiQ 4-bit is a higher-quality quant than the stock 4-bit at the same size.
SmolLM3 · 1 alias
Hugging Face's small-but-mighty 3B — strong sub-4 GB chat model with long-context training.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| smollm3-3b-4bit | mlx-community/SmolLM3-3B-4bit | hermes | qwen3 | spec |
Notes & caveats
- SmolLM3 3B 4-bit is a strong sub-4 GB chat model — see the notable-small-models callout for context.
Nanbeige · 1 alias
Small instruction-tuned checkpoint kept for research diversity.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| nanbeige4.1-3b-4bit | mlx-community/Nanbeige4.1-3B-4bit | hermes | deepseek_r1 | spec |
Nemotron · 2 aliases
Pruning-research checkpoint with hybrid cache — useful for studying compression-vs-quality trade-offs.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| nemotron-3.5-lightning-30b-4bit | mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit | nemotron | qwen3 | hybrid · moe |
| nemotron-30b-4bit | lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bit | hermes | qwen3 | hybrid · moe |
Notes & caveats
- Nemotron 30B is a pruning-research checkpoint with hybrid cache.