SmolLM2 135M Bnb 4bit is an open-source language model by unsloth. Features: 135m LLM, VRAM: 0.1GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.16.
| LLM Name | SmolLM2 135M Bnb 4bit |
| Repository ๐ค | https://huggingface.co/unsloth/SmolLM2-135M-bnb-4bit |
| Base Model(s) | |
| Model Size | 135m |
| Required VRAM | 0.1 GB |
| Updated | 2026-04-09 |
| Maintainer | unsloth |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 49153 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 135M Instruct Bnb 4bit | 8K / 0.1 GB | 1213 | 3 |
| SmolLM2 135M Instruct Q8 Mlx | 8K / 0.1 GB | 67 | 2 |
| SmolLM 135M Instruct 4bit | 2K / 0.1 GB | 4438 | 5 |
| SmolLM 135M Instruct 8bit | 2K / 0.1 GB | 14 | 2 |
| SmolLM 135M Instruct Fp16 | 2K / 0.3 GB | 9 | 2 |
| SmolLM2 135M | 8K / 0.3 GB | 988892 | 172 |
| SmolLM2 135M Instruct | 8K / 0.3 GB | 889496 | 302 |
| Smollm2 Helpbot 135M | 8K / 0.3 GB | 1 | 1 |
| BokantLM0.1 135M Deepseek | 8K / 0.5 GB | 6 | 0 |
| SmolLM2 135M Mofbandgap | 8K / 0.3 GB | 5 | 0 |
๐ 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! ๐