Kimi Dev 72B is an open-source, text-to-text chat model created by Moonshot AI. It is designed for software engineering tasks, specifically for autonomously generating patches to resolve issues in code repositories. The model supports capabilities like web search, code execution, and function calling.
Input
Output
Context
131K
Max Output
512
Parameters
72.7B
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.
Download 145 GB · Runs on vLLM v0.32.0 · 9 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 135 GB | 151 GB | 1x NVIDIA B200 SXM (192 GB) |
| INT8 | 67.7 GB | 79.8 GB | 1x NVIDIA H100 NVL (94 GB) |
| INT4 | 33.9 GB | 44.2 GB | 1x Biren BR100 (64 GB) |
Computed by Inferbase from the 72,706,203,648 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.
Kimi Dev 72B has a context window of 131,072 tokens and a maximum output of 512 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Kimi Dev 72B is an open-weight model under the MIT license. You can download and self-host it within the license terms.
Kimi Dev 72B has 72,706,203,648 parameters (72.7B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit); 131K token context window. Each is computed from the model's stated facts and benchmark results.
Kimi Dev 72B 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 Kimi Dev 72B yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Kimi Dev 72B, and Inferbase runs it on your account with the same routing and logs.
The weights take 135.4 GB at FP16 / BF16, 67.7 GB at INT8, 33.9 GB at INT4, computed from the 72,706,203,648 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.