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
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| bonsai-1.7b-unpacked | prism-ml/Bonsai-1.7B-unpacked | hermes | glm4 | spec |
| bonsai-4b-unpacked | prism-ml/Bonsai-4B-unpacked | hermes | glm4 | spec |
| bonsai-8b-unpacked | prism-ml/Bonsai-8B-unpacked | hermes | glm4 | spec |
Notes & caveats
- Bonsai 1.7B / 4B / 8B unpacked variants are research checkpoints — useful for distillation and draft-model experiments.
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 · 1 alias
Pruning-research checkpoint with hybrid cache — useful for studying compression-vs-quality trade-offs.
parser: hermes
| alias | hf repo | tool parser | reasoning | flags |
|---|---|---|---|---|
| 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.