DeepSeek R1 Distill 7B

DeepSeek

Lightweight reasoning model distilled from DeepSeek R1 into Qwen2.5-Math-7B. Surprisingly strong chain-of-thought for its size.

Text Generation Local DeepSeek Family vR1
Documentation Back to Models
Parameters
7B
params
Context Window
131K
tokens
Max Output
-
tokens
Input Price
-
per 1M tokens
Output Price
-
per 1M tokens

DeepSeek Family Timeline 13 versions

DeepSeek V3.2 Latest local
Dec 2025
DeepSeek V3.2 Exp Latest api
Sep 2025
DeepSeek V3.1 api
Aug 2025
DeepSeek R1 (May) api
May 2025
DeepSeek V3 (March) api
Mar 2025
DeepSeek R1 Distill 7B Current local
Jan 2025
DeepSeek R1 Distill 32B local
Jan 2025
DeepSeek R1 api
Jan 2025
DeepSeek Coder 6.7B local
Nov 2024
DeepSeek Coder 33B local
Nov 2024
DeepSeek V2 Lite 16B local
May 2024
DeepSeek Chat api
-
DeepSeek Coder api
-

Capabilities

👁️
Vision
⚡
Function Calling
📋
JSON Mode
🌊
Streaming
💬
System Prompt
🖥️
Code Execution
🔍
Web Search
🔌
MCP Support

Local Model Specs

Quantization
Q4_K_M
Architecture
Dense (Qwen2.5-Math base)
Runtime
Ollama / llama.cpp
Disk Size
4.7 GB

Details

Release Date
January 22, 2025
Knowledge Cutoff
-
Source
Local
License
Apache 2.0
Model ID
deepseek-r1-distill-7b
Last updated: March 13, 2026