PrimeIntellect INTELLECT 3.1 needs about 72.5 GB of memory at Q4_K_M (a 70.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 0.2 GB to 213.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.2 GB.
PrimeIntellect INTELLECT 3.1 is a 107B-parameter Intellect model in GGUF format, quantized by wimmmm. Its trained context length is 128K tokens. The repository has 8 quant files, from 0.2 GB to 213.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 2.3 GB | Fits | Get file → | |
| IQ2_M | 43.0 GB | 45.1 GB | Too big | Get file → | |
| IQ3_M | 51.4 GB | 53.5 GB | Too big | Get file → | |
| IQ4_NL | 60.4 GB | 62.4 GB | Too big | Get file → | |
| Q4_K_M | 70.4 GB | 72.5 GB | Too big | Get file → | |
| Q5_K_M | 80.6 GB | 82.7 GB | Too big | Get file → | |
| Q6_K | 95.9 GB | 97.9 GB | Too big | Get file → | |
| BF16 | 213.8 GB | 215.8 GB | Too big | Get file → |
What GPU do you need for PrimeIntellect 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: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 2.3 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (43.0 GB file, about 45.1 GB in use).
Which PrimeIntellect INTELLECT 3.1 quant should you choose?
Q4_K_M is the usual starting point for PrimeIntellect INTELLECT 3.1: it balances file size and quality well. Here it is a 70.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about PrimeIntellect INTELLECT 3.1
How much VRAM does PrimeIntellect INTELLECT 3.1 need?
About 72.5 GB at Q4_K_M with an 8K context window. That is the 70.4 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 PrimeIntellect INTELLECT 3.1 on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of PrimeIntellect INTELLECT 3.1 GGUF?
It depends on the quant: file is 0.2 GB, IQ2_M is 43.0 GB, IQ3_M is 51.4 GB, IQ4_NL is 60.4 GB, Q4_K_M is 70.4 GB, Q5_K_M is 80.6 GB and 2 more.
What context length does PrimeIntellect 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 PrimeIntellect INTELLECT 3.1 GGUF?
The files are on Hugging Face in the wimmmm/PrimeIntellect-INTELLECT-3.1-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 PrimeIntellect 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.