SmolLM3 3B Bf16 is an open-source language model by mlx-community. Features: 3b LLM, VRAM: 6.1GB, Context: 64K, License: apache-2.0, LLM Explorer Score: 0.2.
| LLM Name | SmolLM3 3B Bf16 |
| Repository 🤗 | https://huggingface.co/mlx-community/SmolLM3-3B-bf16 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.1 GB |
| Updated | 2026-05-01 |
| Maintainer | mlx-community |
| Model Type | smollm3 |
| Model Files | |
| Supported Languages | en fr es it pt zh ar ru |
| Model Architecture | SmolLM3ForCausalLM |
| License | apache-2.0 |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.54.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|im_end|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM3 3B 128K | 128K / 6.2 GB | 79 | 1 |
| SmolLM3 3B | 64K / 6.2 GB | 112042 | 948 |
| DANTE Mosaic 3.5B | 64K / 6.2 GB | 247 | 0 |
| SmolLM3 3B Base | 64K / 6.2 GB | 38725 | 155 |
| SmolLM3 3B | 64K / 6.2 GB | 2051 | 7 |
| SmolLM3 3B Base | 64K / 6.2 GB | 268 | 5 |
| EMOTRON 3B | 64K / 6.2 GB | 20 | 0 |
| Petite Elle L Aime 3 Sft | 4K / 6.2 GB | 34 | 1 |
| SmolLM3 3B 4bit | 64K / 1.7 GB | 3294 | 6 |
| SmolLM3 3B Unsloth Bnb 4bit | 64K / 2.1 GB | 555 | 3 |
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟