DeepSeek Coder 1.3B
1.4 GB • 131k ctx • Q8_0
← All models4K 1.8 GB 8K 1.9 GB 16K 2 GB 33K 2.1 GB 66K 2.2 GB 131K 2.3 GB
DeepSeek2024
DeepSeek Coder
Dense coding
A compact coding line for completion, explanation, and small refactors. The 1.3B and 6.7B sizes are practical daily drivers on laptops.
- Fits fromPhone / edge · 5 GB+
- Contextup to 131K
- Sizes3
- RunsLocal on Delta
CodingCode completionExplanationsLaptop coding
Sizes
Memory at context length
Approximate working set for DeepSeek Coder 1.3B as context grows.
Related families
DeepSeek R1
Open reasoning distillations that punch above their size: chain-of-thought without a closed API.
Qwen 3.8
Qwen 3.8 Distill models: highly efficient and capable models optimized for edge and desktop.
Qwen3
Think when you need it, answer fast when you don’t: coding, math, and 119 languages, local.