Local LLM model page

DeepCoder (14B)

O3-mini level open coder. Strong reasoning + coding combo. 326K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
14B
Minimum RAM
12 GB
Model size
8.5 GB
Quantization
Q4_K_M

Can DeepCoder (14B) run locally?

DeepCoder (14B) is best suited for mainstream Macs and PCs with 16 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 12 GB RAM.

Search term for LM Studio or compatible runtimes: deepcoder-14b-preview

Hugging Face repository: deepseek-ai/DeepCoder-14B-Preview-GGUF

codereasoningpower

Strengths

  • O3-mini level open coder. Strong reasoning + coding combo. 326K downloads.

Limitations

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

Best use cases

  • code
  • reasoning
  • power

Benchmarks

Speed: 6/10

Quality: 8/10

Coding: 9/10

Reasoning: 8/10

Technical details

Developer: deepcoder

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-03