INTELLECT 3 mxfp4 needs about 62.7 GB of memory at MXFP4 (a 60.7 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 6.3 GB.
INTELLECT 3 mxfp4 is a 107B-parameter Intellect model in GGUF format, quantized by jivank. Its trained context length is 128K tokens. The repository has 1 quant file, from 60.7 GB (MXFP4) to 60.7 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 60.7 GB | 62.7 GB | Too big | Get file → |
What GPU do you need for INTELLECT 3 mxfp4?
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 INTELLECT 3 mxfp4 quant should you choose?
MXFP4 (60.7 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 INTELLECT 3 mxfp4
How much VRAM does INTELLECT 3 mxfp4 need?
About 62.7 GB at MXFP4 with an 8K context window. That is the 60.7 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 INTELLECT 3 mxfp4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 62.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of INTELLECT 3 mxfp4 GGUF?
It depends on the quant: MXFP4 is 60.7 GB.
What context length does INTELLECT 3 mxfp4 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download INTELLECT 3 mxfp4 GGUF?
The files are on Hugging Face in the jivank/INTELLECT-3-mxfp4-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 INTELLECT 3 mxfp4 use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.