Kimi K3 — Hardware Requirements & GPU Compatibility
VisionChatKimi K3 is a 2779.9B-parameter open language model from Moonshot AI in the Kimi K3 family. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 5565.62 GB of VRAM — see which GPUs and Macs can run it below.
Specifications
- Publisher
- Moonshot AI
- Family
- Kimi K3
- Parameters
- 2779.9B
- Architecture
- KimiK3ForConditionalGeneration
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 163,840
- Release Date
- 2026-06-13
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Kimi K3 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 5565.6 GB | 8356.2 GB | 5559.86 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Kimi K3?
BF16 · 5565.6 GBKimi K3 (BF16) requires 5565.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7236+ GB is recommended. Using the full 1049K context window can add up to 2790.6 GB, bringing total usage to 8356.2 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Where to Download Kimi K3
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Frequently Asked Questions
- How much VRAM does Kimi K3 need?
Kimi K3 requires 5565.6 GB of VRAM at BF16. Full 1049K context adds up to 2790.6 GB (8356.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2779.9B × 16 bits ÷ 8 = 5559.9 GB
KV Cache + Overhead ≈ 5.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2796.3 GB (at full 1049K context)
VRAM usage by quantization
BF165565.6 GBBF16 + full context8356.2 GB- Can NVIDIA GeForce RTX 5090 run Kimi K3?
No — Kimi K3 requires at least 5565.6 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Kimi K3 on a Mac?
Kimi K3 requires at least 5565.6 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Kimi K3 locally?
Yes — Kimi K3 can run locally on consumer hardware. At BF16 quantization it needs 5565.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- What's the download size of Kimi K3?
At BF16, the download is about 5559.86 GB.
- Which GPUs can run Kimi K3?
No single consumer GPU has enough VRAM to run Kimi K3 at BF16 (5565.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Kimi K3?
Kimi K3 requires at least 5565.6 GB at BF16, which exceeds the unified memory of most consumer devices. A high-memory Mac Studio, Mac Pro, or multi-GPU desktop setup is recommended.