MiMo 7B RL Zero is an open-source chat model created by Xiaomi that takes and returns text. It is a reasoning-focused language model built from scratch and designed for mathematics and code tasks.
Input
Output
Context
33K
Max Output
-
Parameters
7.8B
Input Modalities
Output Modalities
None the catalog can show from stated facts or measured scores.
Download 15.7 GB · Runs on vLLM v0.32.0
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 14.6 GB | 18.8 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT8 | 7.30 GB | 11.1 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 3.65 GB | 7.30 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 7,833,409,536 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.
MiMo 7B RL Zero has a context window of 32,768 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. MiMo 7B RL Zero is an open-weight model under the MIT license. You can download and self-host it within the license terms.
MiMo 7B RL Zero has 7,833,409,536 parameters (7.8B), 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.
MiMo 7B RL 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 MiMo 7B RL Zero yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves MiMo 7B RL Zero, and Inferbase runs it on your account with the same routing and logs.
The weights take 14.6 GB at FP16 / BF16, 7.3 GB at INT8, 3.6 GB at INT4, computed from the 7,833,409,536 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.