Local LLM model page

DeepScaleR (1.5B)

Tiny model beating o1-preview on math! Incredible reasoning-to-size ratio. 474K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
1.5B
Minimum RAM
4 GB
Model size
1 GB
Quantization
Q5_K_M

Can DeepScaleR (1.5B) run locally?

DeepScaleR (1.5B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 4 GB RAM.

Search term for LM Studio or compatible runtimes: deepscaler-1.5b

Hugging Face repository: agentica-org/DeepScaleR-1.5B-Preview-GGUF

reasoninglightspeed

Strengths

  • Tiny model beating o1-preview on math! Incredible reasoning-to-size ratio. 474K downloads.

Limitations

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

Best use cases

  • reasoning
  • light
  • speed

Benchmarks

Speed: 10/10

Quality: 5/10

Coding: 4/10

Reasoning: 8/10

Technical details

Developer: deepscaler

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-02