moonshotai.Kimi K2.5 BF16 needs about 622.1 GB of memory at Q4_K_M (a 620.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 267.1 GB (IQ2_XXS) to 620.6 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
moonshotai.Kimi K2.5 BF16 is a 1030B-parameter Kimi model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 5 quant files, from 267.1 GB (IQ2_XXS) to 620.6 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 267.1 GB (19 parts) | 268.7 GB | Too big | Get file → | |
| Q2_K | 372.9 GB (26 parts) | 374.5 GB | Too big | Get file → | |
| Q3_K_M | 489.1 GB (37 parts) | 490.7 GB | Too big | Get file → | |
| MXFP4_MOE | 551.7 GB (37 parts) | 553.3 GB | Too big | Get file → | |
| Q4_K_M | 620.6 GB (42 parts) | 622.1 GB | Too big | Get file → |
What GPU do you need for moonshotai.Kimi K2.5 BF16?
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 moonshotai.Kimi K2.5 BF16 quant should you choose?
Q4_K_M is the usual starting point for moonshotai.Kimi K2.5 BF16: it balances file size and quality well. Here it is a 620.6 GB file.
If memory is tight, the smallest file is IQ2_XXS at 267.1 GB, with the quality trade-offs that come with fewer bits. 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 moonshotai.Kimi K2.5 BF16
How much VRAM does moonshotai.Kimi K2.5 BF16 need?
About 622.1 GB at Q4_K_M with an 8K context window. That is the 620.6 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 moonshotai.Kimi K2.5 BF16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 268.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of moonshotai.Kimi K2.5 BF16 GGUF?
It depends on the quant: IQ2_XXS is 267.1 GB, Q2_K is 372.9 GB, Q3_K_M is 489.1 GB, MXFP4_MOE is 551.7 GB, Q4_K_M is 620.6 GB.
What context length does moonshotai.Kimi K2.5 BF16 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download moonshotai.Kimi K2.5 BF16 GGUF?
The files are on Hugging Face in the DevQuasar/moonshotai.Kimi-K2.5-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 moonshotai.Kimi K2.5 BF16 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.