Kolibri 1 MXFP4 GGUF MxWave needs about 46.8 GB of memory at MXFP4 (a 45.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.
Kolibri 1 MXFP4 GGUF MxWave is a 78.1B-parameter Kolibri model in GGUF format, quantized by kirillbilchenko. Its trained context length is 256K tokens. The repository has 1 quant file, from 45.4 GB (MXFP4) to 45.4 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 45.4 GB | 46.8 GB | Too big | Get file → |
What GPU do you need for Kolibri 1 MXFP4 GGUF MxWave?
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: the best quant that fits is MXFP4 (45.4 GB file, about 46.8 GB in use).
Which Kolibri 1 MXFP4 GGUF MxWave quant should you choose?
MXFP4 (45.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kolibri 1 MXFP4 GGUF MxWave
How much VRAM does Kolibri 1 MXFP4 GGUF MxWave need?
About 46.8 GB at MXFP4 with an 8K context window. That is the 45.4 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 Kolibri 1 MXFP4 GGUF MxWave on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 46.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kolibri 1 MXFP4 GGUF MxWave GGUF?
It depends on the quant: MXFP4 is 45.4 GB.
What context length does Kolibri 1 MXFP4 GGUF MxWave support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.4 GB at 32K.
Where can I download Kolibri 1 MXFP4 GGUF MxWave GGUF?
The files are on Hugging Face in the kirillbilchenko/Kolibri-1-MXFP4-GGUF-MxWave repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kolibri 1 MXFP4 GGUF MxWave use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.