Local LLM model page

SmolLM 2 (1.7B)

Ultra-compact HuggingFace model. Surprisingly capable for its tiny size. 1.9M downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
1.7B
Minimum RAM
4 GB
Model size
1 GB
Quantization
Q8_0

Can SmolLM 2 (1.7B) run locally?

SmolLM 2 (1.7B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q8_0 as the default quantization, with at least 4 GB RAM.

Search term for LM Studio or compatible runtimes: smollm2-1.7b-instruct

Hugging Face repository: HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF

chatlightspeed

Strengths

  • Ultra-compact HuggingFace model. Surprisingly capable for its tiny size. 1.9M downloads.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • light
  • speed

Benchmarks

Speed: 10/10

Quality: 4/10

Coding: 3/10

Reasoning: 3/10

Technical details

Developer: smollm

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-11