DeepSeek V2.5 is an open-source chat model created by DeepSeek. It is designed for general conversation and code generation tasks, taking in and outputting text.
Input
Output
Context
131K
Max Output
8K
Parameters
235.7B
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.
None the catalog can show from stated facts or measured scores.
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 439 GB | 472 GB | 2x NVIDIA B300 SXM (576 GB) |
| INT8 | 220 GB | 242 GB | 1x NVIDIA B300 SXM (288 GB) |
| INT4 | 110 GB | 126 GB | 1x NVIDIA B200 SXM (192 GB) |
Computed by Inferbase from the 235,741,434,880 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 10, 2026.
Answered from the facts on this page, with their sources.
DeepSeek V2.5 has a context window of 131,072 tokens and a maximum output of 8,192 tokens (source: Inferbase review). A provider may serve less; Inferbase routes on what each provider serves.
Yes. DeepSeek V2.5 is an open-weight model under the Other license. You can download and self-host it within the license terms.
DeepSeek V2.5 has 235,741,434,880 parameters (235.7B), as stated in the creator's Hugging Face repository.
DeepSeek V2.5 accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
DeepSeek V2.5 has published results from Artificial Analysis. The Benchmarks card shows each score as reported, with its band among the models the same source measured. Scores are never combined across sources.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves DeepSeek V2.5, and Inferbase runs it on your account with the same routing and logs.
The weights take 439.1 GB at FP16 / BF16, 219.6 GB at INT8, 109.8 GB at INT4, computed from the 235,741,434,880 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.
Start on the free plan with 5,000 requests a month, no card required.