Qwen2.5-Coder-0.5B
Tiny open Qwen code model for lightweight completion and on-device coding.
- Capability
- 68.0ECI · #158 of 158
- Input
- —No listed price
- Output
- —No listed price
- Context
- 33K8K max output
What it costs
No per-token price is published for this model yet.
No per-token price is listed for this model on models.dev.
Independent benchmarks
#158 of 158 scored models
The shaded band is Epoch AI’s confidence range (49.0–83.6); the tick marks the median scored model.
Scores from Epoch AI, run independently of Alibaba (Qwen).
The details
- Lab
- Alibaba (Qwen)
- Released
- Nov 12, 2024
- Context window
- 32,768 tokens
- Max output
- 8,192 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Weights
- Open weights · Apache 2.0
More from Alibaba (Qwen)
About Qwen2.5-Coder-0.5B
How much does Qwen2.5-Coder-0.5B cost?
Qwen2.5-Coder-0.5B has no published per-token API price on models.dev yet.
What is the context window of Qwen2.5-Coder-0.5B?
Qwen2.5-Coder-0.5B accepts up to 32,768 tokens per request and can write up to 8,192 tokens in one response.
How good is Qwen2.5-Coder-0.5B?
Epoch AI gives Qwen2.5-Coder-0.5B a Capabilities Index score of 68.0 (likely range 49.0–83.6), ranking it #158 of 158 models Epoch has scored.
Is Qwen2.5-Coder-0.5B open source?
Yes. Alibaba (Qwen) publishes the weights under the Apache 2.0 licence, so it can be downloaded and self-hosted.
What inputs does Qwen2.5-Coder-0.5B support?
Qwen2.5-Coder-0.5B accepts text and replies in text. It is not a dedicated reasoning model, does not support tool calling.
When was Qwen2.5-Coder-0.5B released?
Alibaba (Qwen) released Qwen2.5-Coder-0.5B on Nov 12, 2024.
What are the best alternatives to Qwen2.5-Coder-0.5B?
The closest current models from other labs on capability, price and release date are Mistral Large 2.1 (Mistral AI, $2.00 / $6.00), Aya Expanse 32B (Cohere, $0.50 / $1.50), Nova Lite (Amazon, $0.06 / $0.24) and Gemini 2.0 Flash-Lite (Google, $0.064 / $0.255).