Local LLM model page

DeepSeek Coder (33B)

DeepSeek code specialist. Excellent at code generation and completion. 1.4M downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
33B
Minimum RAM
24 GB
Model size
19 GB
Quantization
Q4_K_M

Can DeepSeek Coder (33B) run locally?

DeepSeek Coder (33B) is best suited for power-user machines with 32 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 24 GB RAM.

Search term for LM Studio or compatible runtimes: deepseek-coder-33b-instruct

Hugging Face repository: TheBloke/deepseek-coder-33B-instruct-GGUF

codepower

Strengths

  • DeepSeek code specialist. Excellent at code generation and completion. 1.4M downloads.

Limitations

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

Best use cases

  • code
  • power

Benchmarks

Speed: 4/10

Quality: 7/10

Coding: 9/10

Reasoning: 7/10

Technical details

Developer: deepseek

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-01