IN

INTELLECT 3.1

IntellectGGUF by noctrexUpdated 2026-02-19
Download on Hugging Face
Parameters107B
Context128K
Layers46
Architectureglm4moe
Smallest quant67.4 GB
Quick answer

INTELLECT 3.1 needs about 69.4 GB of memory at MXFP4_MOE (a 67.4 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 6.2 GB.

INTELLECT 3.1 is a 107B-parameter Intellect model in GGUF format, quantized by noctrex. Its trained context length is 128K tokens. The repository has 1 quant file, from 67.4 GB (MXFP4_MOE) to 67.4 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE67.4 GB (4 parts) 69.4 GB
Too big Get file →

What GPU do you need for INTELLECT 3.1?

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 3.1 quant should you choose?

MXFP4_MOE (67.4 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

Architectureglm4moe
Parameters107B (approximate, mixture of experts)
Layers46
Trained context131,072 tokens
KV cache (fp16)184 KB per token

Source

Quantized bynoctrex
FamilyIntellect
Licensemit
Downloads (HF)12
Last updated2026-02-19

Frequently asked questions about INTELLECT 3.1

How much VRAM does INTELLECT 3.1 need?

About 69.4 GB at MXFP4_MOE with an 8K context window. That is the 67.4 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 INTELLECT 3.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 69.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of INTELLECT 3.1 GGUF?

It depends on the quant: MXFP4_MOE is 67.4 GB.

What context length does INTELLECT 3.1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.5 GB at 8K and 6.2 GB at 32K.

Where can I download INTELLECT 3.1 GGUF?

The files are on Hugging Face in the noctrex/INTELLECT-3.1-MXFP4_MOE-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 3.1 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.

Other GGUFs of INTELLECT-3.1

Similar models

Browse all →

More from noctrex

All by noctrex →

More Intellect models

All Intellect →

Other large models

All large models →