Kimi-K3
Support summary
Kimi-K3 is a checkpoint published by Moonshot AI, built on the KimiK3ForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. Official recipes or cookbooks cover SGLang, without pinning a stable release.
vLLM documents support in 3 of 20 indexed releases, from 0.27.0 to 0.28.0.
- Documented hardware
- Ascend NPU, NVIDIA / CUDA, and AMD / ROCm
- Documented quantization
- default and MXFP4
- Documented features
- Reasoning parsers, Tensor parallelism, and Tool calling
- Configured context
- 1,048,576 tokens
- License
- kimi-k3
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Moonshot AI
- Task
- image text to text
- License
- kimi-k3
- Library
- transformers
- Architecture
- KimiK3ForConditionalGeneration
- Weight tensor elements
- 2.8T
- Tensor types
- F32, BF16, U8
- Quantization
- compressed-tensors · mxfp4-pack-quantized
- Configured context
- 1,048,576 tokens
- Weight access
- Public
- Repository created
- 2026-06-13
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 3 indexed revisions, v0.27.0 to v0.28.0
- moonshotai/Kimi-K3 · publisher model card
- moonshotai/Kimi-K3 · Hugging Face metadata
- moonshotai/Kimi-K3 · publisher configuration
- vllm · models/moonshotai/Kimi-K3.yaml
- sglang · docs/src/snippets/configs/moonshotai/kimi-k3.jsx
- sglang · docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/Moonshotai/Kimi-K3.mdxSource 2: sglang · docs/src/snippets/_deployment.jsxSource 3: sglang · docs/src/snippets/configs/moonshotai/kimi-k3.jsxSource 4: sglang · docs/src/snippets/configs/moonshotai/kimi-k3-benchmarks.jsxSource 5: sglang · docs/src/snippets/_kimi_k3_mamba_ratio_calculator.jsxSource 6: sglang · docs/src/snippets/_playground.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||