DeepSeek R1 Zero is an open-source chat model created by DeepSeek. It is a reasoning model trained via large-scale reinforcement learning without supervised fine-tuning, designed for complex tasks like mathematics and coding.
Input
Output
Context
131K
Max Output
33K
Parameters
684.5B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 1275 GB | 1357 GB | 4x AMD Instinct MI455X (1728 GB) |
| INT8 | 638 GB | 688 GB | 2x AMD Instinct MI455X (864 GB) |
| INT4 | 319 GB | 353 GB | 1x AMD Instinct MI455X (432 GB) |
Computed by Inferbase from the 684,531,386,000 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 11, 2026.
Answered from the facts on this page, with their sources.
DeepSeek R1 Zero has a context window of 131,072 tokens and a maximum output of 32,768 tokens (source: Inferbase review). A provider may serve less; Inferbase routes on what each provider serves.
Yes. DeepSeek R1 Zero is an open-weight model under the MIT license. You can download and self-host it within the license terms.
DeepSeek R1 Zero has 684,531,386,000 parameters (684.5B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit). Each is computed from the model's stated facts and benchmark results.
DeepSeek R1 Zero 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 DeepSeek R1 Zero yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves DeepSeek R1 Zero, and Inferbase runs it on your account with the same routing and logs.
The weights take 1.28 TB at FP16 / BF16, 637.5 GB at INT8, 318.8 GB at INT4, computed from the 684,531,386,000 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.