LLM EXPLORER 59,766 MODELS INDEXED

SmolLM 135M Instruct by HuggingFaceTB

By HuggingFaceTB · 25475 downloads
HF Repo ↗ Copy URL

SmolLM 135M Instruct is an open-source language model by HuggingFaceTB. Features: 135m LLM, VRAM: 0.3GB, Context: 2K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.2.

  Alignment-handbook Base model:huggingfacetb/smoll... Base model:quantized:huggingfa...   Conversational Dataset:bigcode/self-oss-instr... Dataset:huggingfacetb/everyday... Dataset:magpie-align/magpie-pr...   Dataset:teknium/openhermes-2.5   Deploy:azure   En   Endpoints compatible   Instruct   Llama   Onnx   Region:us   Safetensors   Sft   Trl
Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct 

SmolLM 135M Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
General knowledge questions, Creative writing, Basic Python programming
Limitations:
English only, May have difficulty with arithmetics, editing tasks and complex reasoning
Considerations:
Use as assistive tools rather than definitive sources of information
Supported Languages 
en (proficient)
Training Details 
Data Sources:
Magpie-Align/Magpie-Pro-300K-Filtered, bigcode/self-oss-instruct-sc2-exec-filter-50k, teknium/OpenHermes-2.5, HuggingFaceTB/everyday-conversations-llama3.1-2k
Data Volume:
262k tokens per batch, 1 epoch
Methodology:
Fine-tuned on publicly available datasets
Input Output 
Input Format:
Messages as JSON with role and content fields.
Accepted Modalities:
text
Output Format:
Generated responses as text.
Performance Tips:
Use temperature 0.2 and top-p 0.9 for better sampling.
Release Notes 
Version:
v0.1
Notes:
Initial release. Fine-tuned with stated datasets and DPO.
Version:
v0.2
Notes:
Improved dataset mix for small models and changes in fine-tuning strategy for better topic coherence.
LLM NameSmolLM 135M Instruct
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct 
Base Model(s)  SmolLM 135M   HuggingFaceTB/SmolLM-135M
Model Size135m
Required VRAM0.3 GB
Updated2026-08-02
MaintainerHuggingFaceTB
Model Typellama
Instruction-BasedYes
Model Files  0.3 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.42.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM 135M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Digest Sft28K / 0.5 GB1780
SmolLM2 135M Instruct8K / 0.3 GB1857297388
SmolLM2 135M Reasoning 5K8K / 0.3 GB2763
... Subtitle Postprocessor Merged8K / 0.5 GB161
SmolLM2 135M Instruction Tuned8K / 0.3 GB100
SmolLM2 Rethink 135M8K / 0.5 GB62
SmolLM2 135M Instruct8K / 0.3 GB48873
SmolLM2 135M Instruct Ita8K / 0.1 GB240
...molLM2 135M Instruct Reasoning8K / 0.3 GB70
...wre324 R1 SmolLM2 135M Distill8K / 0.5 GB80
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM-135M-Instruct.