Local LLM model page

Qwen2 Math (72B)

Qwen2 math specialist beating GPT4o on math benchmarks. 173K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
72B
Minimum RAM
64 GB
Model size
42 GB
Quantization
Q4_K_M

Can Qwen2 Math (72B) run locally?

Qwen2 Math (72B) is best suited for high-end workstations with 64 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 64 GB RAM.

Search term for LM Studio or compatible runtimes: qwen2-math-72b-instruct

Hugging Face repository: Qwen/Qwen2-Math-72B-Instruct-GGUF

reasoningquality

Strengths

  • Qwen2 math specialist beating GPT4o on math benchmarks. 173K downloads.

Limitations

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

Best use cases

  • reasoning
  • quality

Benchmarks

Speed: 2/10

Quality: 9/10

Coding: 7/10

Reasoning: 10/10

Technical details

Developer: qwen

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-08