Kimi K3 Uncensored needs about 675.1 GB of memory at IQ1_S (a 579.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 380.3 GB.
Kimi K3 Uncensored – 2.8T parameter, 1M token context, multimodal LLM
Kimi K3 Uncensored is a 2.8T‑parameter model with 104B active parameters and 896 experts. It supports a 1‑million‑token context window and native vision via MoonViT‑V2. The model is released in a single IQ1_S GGUF quantization.
Good at
- Long‑horizon coding
- Multimodal reasoning
- Large context handling
Limits
- Requires >600 GB VRAM
- Large memory footprint
- No refusal data available
Best for
- Extensive codebase analysis
- Research with multimodal inputs
- Long‑form content generation
Who it’s for. Researchers and developers needing a high‑capacity multimodal model with an extremely long context window. Suitable for advanced AI research and experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 579.5 GB (34 parts) | 675.1 GB | Too big | Get file → |
The only available quant is IQ1_S, 579.51 GB file size, estimated 675.1 GB VRAM at 8 k context. This is the recommended quant for users with very large memory budgets; for smaller budgets no other quant is available.
What GPU do you need for Kimi K3 Uncensored?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Kimi K3 Uncensored quant should you choose?
IQ1_S (579.5 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kimi K3 Uncensored
How much VRAM does Kimi K3 Uncensored need?
About 675.1 GB at IQ1_S with an 8K context window. That is the 579.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Kimi K3 Uncensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 675.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kimi K3 Uncensored GGUF?
It depends on the quant: IQ1_S is 579.5 GB.
What context length does Kimi K3 Uncensored support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 95.1 GB at 8K and 380.3 GB at 32K.
Where can I download Kimi K3 Uncensored GGUF?
The files are on Hugging Face in the Ryanchen911/Kimi-K3-Uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kimi K3 Uncensored use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Kimi K3 Uncensored on 8 GB VRAM?
No. The IQ1_S quant requires approximately 675.1 GB VRAM at 8 k context, far beyond 8 GB.
Does Kimi K3 Uncensored support a 1‑million‑token context?
Yes. The model was trained with a 1,048,576‑token context window.
Is vision support included in this model?
Yes. It uses the MoonViT‑V2 vision encoder with 401M parameters.