DeepSeekOpen Weights
DeepSeek-R1-Distill-Qwen-32B
Reasoning Model • Released 2025-01-14 • Last Verified 2025-02-01
DeepSeek-R1-Distill-Qwen-32B - DeepSeek open-source frontier model for math, reasoning, and code.
Context Window128k
LicenseMIT License
Deployment
Cloud API Local Run
API AvailableYes (REST/SDK)
Benchmark Performance
MATH / Code93
Hardware Requirements for Local Running
24GB-48GB VRAM
Strengths
- •High accuracy
- •Fast inference
Limitations & Weaknesses
- •Closed source API
API Sample CodePython / REST
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
model="deepseek-r1-distill-qwen-32b",
messages=[
{"role": "system", "content": "You are a helpful expert assistant."},
{"role": "user", "content": "Explain quantum computing in 2 sentences."}
]
)
print(response.choices[0].message.content)Pricing Overview
MIT Open Source
Prices subject to provider tiers and volume discounts. Check documentation for current token rates.
Model Tags
#deepseek#mit-license#reasoning#local
Similar Models from DeepSeek
DeepSeek
Open Weights
DeepSeek-R1
Reasoning Model
DeepSeek-R1 - DeepSeek open-source frontier model for math, reasoning, and code.
Context Window128k
MATH / Code80
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights
DeepSeek-R1-Zero
Reasoning Model
DeepSeek-R1-Zero - DeepSeek open-source frontier model for math, reasoning, and code.
Context Window128k
MATH / Code81
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights
DeepSeek-V3
MoE LLM
DeepSeek-V3 - DeepSeek open-source frontier model for math, reasoning, and code.
Context Window128k
MATH / Code82
Cloud API Local Run
#deepseek#mit-license