LLM EXPLORER 59,420 MODELS INDEXED

SmolGRPO 135M by mlabonne

By mlabonne · 12 downloads

SmolGRPO 135M is an open-source language model by mlabonne. Features: 135m LLM, VRAM: 0.3GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.17.

  Conversational   Endpoints compatible   Grpo   Instruct   Llama   Region:us   Safetensors   Trl
Model Card on HF πŸ€—: https://huggingface.co/mlabonne/SmolGRPO-135M 

SmolGRPO 135M Parameters and Internals

LLM NameSmolGRPO 135M
Repository πŸ€—https://huggingface.co/mlabonne/SmolGRPO-135M 
Model Size135m
Required VRAM0.3 GB
Updated2026-08-05
Maintainermlabonne
Model Typellama
Instruction-BasedYes
Model Files  0.3 GB
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.47.1
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolGRPO 135M

Best Alternatives
Context / RAM
Downloads
Likes
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
...rtis SmolLM2 135M Instruct DPO8K / 0.5 GB210
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/SmolGRPO-135M.