Qwen 2.5 Coder 32B Instruct is an open-source chat model from Qwen designed for code-related tasks. It processes and generates text, with capabilities for function calling, structured output, and parallel tool calls through its API. The model is built for code generation, reasoning, and fixing, as well as for applications like code agents.
Input
Output
Context
33K
Max Output
8K
Parameters
32.8B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 61.0 GB | 69.3 GB | 1x NVIDIA A100 PCIe 80GB (80 GB) |
| INT8 | 30.5 GB | 37.3 GB | 1x Moore Threads MTT S4000 (48 GB) |
| INT4 | 15.3 GB | 21.2 GB | 1x Tenstorrent Blackhole p150 (32 GB) |
Computed by Inferbase from the 32,763,876,352 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 15, 2026.
Answered from the facts on this page, with their sources.
Qwen 2.5 Coder 32B Instruct has a context window of 32,768 tokens and a maximum output of 8,192 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Qwen 2.5 Coder 32B Instruct is an open-weight model under the Apache 2.0 license. You can download and self-host it within the license terms.
Qwen 2.5 Coder 32B Instruct has 32,763,876,352 parameters (32.8B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (apache-2.0). Each is computed from the model's stated facts and benchmark results.
Qwen 2.5 Coder 32B Instruct accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Qwen 2.5 Coder 32B Instruct yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Qwen 2.5 Coder 32B Instruct, and Inferbase runs it on your account with the same routing and logs.
The weights take 61.0 GB at FP16 / BF16, 30.5 GB at INT8, 15.3 GB at INT4, computed from the 32,763,876,352 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of Qwen 2.5 Coder 32B Instruct lists one language: English. That is what Qwen states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.