DeepSeek

3 MLX aliases · DeepSeek R1 reasoning-distilled + Coder MoE — V4-Flash gets its own hero page.

DeepSeek's open-weights line on rapid-mlx covers the R1 reasoning-distilled models and the Coder MoE — both with reasoning_content streaming where appropriate. The frontier 1T-class V4-Flash family lives on its own hero deep dive (see DeepSeek V4-Flash) because the CSA + HCA sparse-attention path needed a vendored kernel and deserves a dedicated writeup.

family

DeepSeek

aliases

3

lines

2

install

rapid-mlx serve <alias>

OpenAI base URL

http://localhost:8000/v1

Lines in this family

• DeepSeek R1 (2 aliases)
• DeepSeek Coder (1 alias)

DeepSeek R1 · 2 aliases

Reasoning-distilled — chain-of-thought weights distilled into compact models that punch above their parameter count on reasoning benchmarks. The 8B variant uses the deepseek_v3 tool parser; the 32B variant uses the more recent deepseek parser. Both stream reasoning_content via the deepseek_r1 reasoning parser.

parser: deepseek

Notes & caveats

• The 32B-4bit quant is the better fit for a 32 GB Mac; the 8B-4bit drops to 16 GB.

DeepSeek Coder · 1 alias

Code-specialised MoE line, kept as a single 16B-Lite alias for users who want a DeepSeek-flavoured coder alongside the Qwen3 Coder family.

parser: —

Notes & caveats

• Lite-MoE means good active-parameter speed-to-quality on a 32 GB+ Mac.

Notes & caveats

• For the frontier 1T-class line see the dedicated DeepSeek V4-Flash hero page.

Where next