IN

INTELLECT 3 REAP 50 Heretic

IntellectGGUF by AkicouUpdated 2026-01-25
Download on Hugging Face
Parameters57B
Context128K
Layers47
Architectureglm4moe
Smallest quant34.5 GB
Quick answer

INTELLECT 3 REAP 50 Heretic needs about 39.5 GB of memory at Q4_K_M (a 37.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 34.5 GB (Q4_K_S) to 60.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

INTELLECT 3 REAP 50 Heretic is a 57B-parameter Intellect model in GGUF format, quantized by Akicou. Its trained context length is 128K tokens. The repository has 7 quant files, from 34.5 GB (Q4_K_S) to 60.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S34.5 GB 36.6 GB
Too big Get file →
Q4_K_M37.4 GB 39.5 GB
Too big Get file →
Q5_039.3 GB 41.4 GB
Too big Get file →
Q5_K_S40.4 GB 42.5 GB
Too big Get file →
Q5_K_M42.9 GB 45.0 GB
Too big Get file →
Q6_K50.9 GB 53.0 GB
Too big Get file →
Q8_060.6 GB 62.7 GB
Too big Get file →

What GPU do you need for INTELLECT 3 REAP 50 Heretic?

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 Q5_K_M (42.9 GB file, about 45.0 GB in use).

Which INTELLECT 3 REAP 50 Heretic quant should you choose?

Q4_K_M is the usual starting point for INTELLECT 3 REAP 50 Heretic: it balances file size and quality well. Here it is a 37.4 GB file.

The Q8_0 file is 60.6 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_K_S at 34.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureglm4moe
Parameters57B (approximate, mixture of experts)
Layers47
Trained context131,072 tokens
KV cache (fp16)188 KB per token

Source

Quantized byAkicou
FamilyIntellect
Licenseapache-2.0
Downloads (HF)352
Last updated2026-01-25

Frequently asked questions about INTELLECT 3 REAP 50 Heretic

How much VRAM does INTELLECT 3 REAP 50 Heretic need?

About 39.5 GB at Q4_K_M with an 8K context window. That is the 37.4 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 REAP 50 Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 36.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of INTELLECT 3 REAP 50 Heretic GGUF?

It depends on the quant: Q4_K_S is 34.5 GB, Q4_K_M is 37.4 GB, Q5_0 is 39.3 GB, Q5_K_S is 40.4 GB, Q5_K_M is 42.9 GB, Q6_K is 50.9 GB and 1 more.

What context length does INTELLECT 3 REAP 50 Heretic 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 REAP 50 Heretic GGUF?

The files are on Hugging Face in the Akicou/INTELLECT-3-REAP-50-heretic-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 REAP 50 Heretic 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.

Similar models

Browse all →

More from Akicou

All by Akicou →

More Intellect models

All Intellect →

Other large models

All large models →