Looking for something different?
Models that trade off differently against the one you are viewing
Better quality
Newer flagship models that generally produce stronger results.
Lower cost per run
Open-source models we host, unlimited on the $149/month plan.
Related Models
Discover similar models you might be interested in
DeepSeek R1 Distill Qwen 1.5B
Reasoning. Laptop-sized.
Compact Power. Serious Reasoning.
- Distilled Intelligence671B Reasoning CompressedKnowledge distilled from massive DeepSeek-R1 into 1.5B parameters without performance loss.
- Hardware Efficient4GB GPU MemoryRuns on single laptop GPU in 8-bit quantization for local deployment and edge inference.
- Chain-of-ThoughtMath and Code MasteryExcels at step-by-step problem solving, mathematical reasoning, and code comprehension tasks.
DeepSeek R1 Distill Qwen 1.5B questions
- What is DeepSeek R1 Distill Qwen 1.5B and how does it work?
- DeepSeek R1 Distill Qwen 1.5B is a compact 1.5B parameter language model that inherits reasoning capabilities from the larger 671B DeepSeek-R1 through knowledge distillation. It uses a dense Transformer architecture with Grouped Query Attention for efficient inference while maintaining strong performance on math, code, and logical reasoning tasks.
- Can I run DeepSeek R1 Distill Qwen 1.5B locally?
- Yes. The model fits on a single laptop GPU using approximately 4GB VRAM in 8-bit quantization, making it ideal for local deployment on consumer-grade hardware without extensive infrastructure.
- What are the primary use cases for this DeepSeek R1 Distill Qwen 1.5B API?
- This model excels in mathematical problem-solving, code comprehension, general text-based reasoning, and any task requiring step-by-step logical inference. It's optimized for resource-constrained environments where computational budget is limited.
- What quantization formats are available?
- The model supports multiple quantization formats including Q2_K, Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0, AWQ Int4, and various MLX quantizations (3bit, 4bit, 6bit, 8bit, bf16) for different performance-memory tradeoffs.
- Is fine-tuning supported for DeepSeek R1 Distill Qwen 1.5B?
- Yes. The model supports fine-tuning using LoRA for efficient customization with your own data to improve responses for specific domains or use cases.
About DeepSeek R1 Distill Qwen 1.5B
Ultra-efficient 1.5B parameter language model fine-tuned for advanced multi-step reasoning and math tasks, optimized for edge deployment with 4-bit and 5-bit quantized versions.
DeepSeek R1 Distill Qwen 1.5B facts
- Provider
- DeepSeek
- Input price
- $0.225 per 1M tokens
- Output price
- $0.225 per 1M tokens
- Added to ModelsLab
- July 22, 2025
- Model ID
- deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B
Key Features
- Chat completion and multi-turn conversation API
- Streaming response with token-by-token output
- Function calling and tool use support
- System prompts and role-based messaging
- JSON mode and structured output
Quick Start
Integrate DeepSeek R1 Distill Qwen 1.5B into your application with a single API call. Get your API key from the pricing page to get started.
import requestsimport jsonurl = "https://modelslab.com/api/v7/llm/chat/completions"headers = {"Content-Type": "application/json"}data = {"model_id": "deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B","messages": [{"role": "user","content": "Hello!"}],"max_tokens": 1000,"key": "YOUR_API_KEY"}try:response = requests.post(url, headers=headers, json=data)response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX)result = response.json()print("API Response:")print(json.dumps(result, indent=2))except requests.exceptions.HTTPError as http_err:print(f"HTTP error occurred: {http_err} - {response.text}")except Exception as err:print(f"Other error occurred: {err}")
const endpointUrl = 'https://modelslab.com/api/v7/llm/chat/completions';const requestBody = {"model_id": "deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B","messages": [{"role": "user","content": "Hello!"}],"max_tokens": 1000,"key": "YOUR_API_KEY"};async function makeApiRequest() {try {const response = await fetch(endpointUrl, {method: 'POST',headers: {'Content-Type': 'application/json',},body: JSON.stringify(requestBody)});if (!response.ok) {let errorResult;try {errorResult = await response.json();} catch (e) {errorResult = { error: { message: await response.text() } };}throw new Error(`API Error (${response.status}): ${errorResult.error?.message || response.statusText || 'Unknown error'}`);}const result = await response.json();console.log('API Response:', result);return result;} catch (error) {console.error('Error making API request:', error.message);throw error;}}makeApiRequest();
curl -X POST "https://modelslab.com/api/v7/llm/chat/completions" \-H "Content-Type: application/json" \-d '{"model_id": "deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B","messages": [{"role": "user","content": "Hello!"}],"max_tokens": 1000,"key": "YOUR_API_KEY"}'
<?php$url = 'https://modelslab.com/api/v7/llm/chat/completions';$headers = ['Content-Type: application/json'];$data = ['model_id' => 'deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B','messages' => [{"role":"user","content":"Hello!"}],'max_tokens' => 1000,'key' => 'YOUR_API_KEY',];$ch = curl_init();curl_setopt($ch, CURLOPT_URL, $url);curl_setopt($ch, CURLOPT_POST, true);curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);curl_setopt($ch, CURLOPT_TIMEOUT, 30);$response = curl_exec($ch);$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);$curlError = curl_error($ch);if ($curlError) {echo 'Curl error: ' . $curlError;} else {echo "HTTP Status Code: " . $httpCode . "\n";$result = json_decode($response, true);if (json_last_error() !== JSON_ERROR_NONE) {echo "Error decoding JSON: " . json_last_error_msg() . "\n";echo "Raw response: " . $response . "\n";} else {echo "API Response:\n";print_r($result);}}?>
Pricing
DeepSeek R1 Distill Qwen 1.5B API costs $0.18 per million tokens. Plans start at $21/month, and open-source models are unlimited on the $149/month plan. View pricing plans
Use Cases
- AI chatbots and virtual assistants
- Code generation and developer tools
- Content writing and copywriting automation
- Data analysis, summarization, and extraction






