SmolLM2 1.7B Instruct Bnb 4bit is an open-source language model by unsloth. Features: 1.7b LLM, VRAM: 1GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.
4-bit 4bit Base model:huggingfacetb/smoll... Base model:quantized:huggingfa... Bitsandbytes Conversational Deploy:azure En Endpoints compatible Instruct Llama Quantized Region:us Safetensors Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-bnb-4bit
SmolLM2 1.7B Instruct Bnb 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
SmolLM2 1.7B Instruct Bnb 4bit Parameters and Internals
| LLM Name | SmolLM2 1.7B Instruct Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/SmolLM2-1.7B-Instruct-bnb-4bit |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 1 GB |
| Updated | 2026-04-09 |
| Maintainer | unsloth |
| Model Type | llama |
| Instruction-Based | Yes |
| 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 to SmolLM2 1.7B Instruct Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM 1.7B Bnb 4bit | 2K / 1 GB | 1054 | 2 |
| SmolLM 1.7B Instruct 4bit | 2K / 1 GB | 194 | 2 |
| SmolLM 1.7B Instruct 8bit | 2K / 1.8 GB | 6 | 1 |
| SmolLM2 1.7B Instruct 16K | 16K / 3.4 GB | 449 | 10 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 104194 | 724 |
| ...ygnis Alpha 1.7B V0.1 Instruct | 8K / 3.4 GB | 522 | 2 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 1853 | 4 |
| SmolTulu 1.7B Reinforced | 8K / 3.4 GB | 10 | 5 |
| SmolLM2 1.7 Persona | 8K / 3.5 GB | 11 | 0 |
| Penny 1.7B | 8K / 6.9 GB | 8 | 24 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/SmolLM2-1.7B-Instruct-bnb-4bit .
Rank the SmolLM2 1.7B Instruct Bnb 4bit Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a