NO

NotQuiteAMoE 32B exp i1

NotquiteamoeGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters158B
Context32K
Layers320
Architectureqwen2
Smallest quant33.2 GB
Quick answer

NotQuiteAMoE 32B exp i1 needs about 53.2 GB of memory at IQ2_XXS (a 42.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 33.2 GB (IQ1_S) to 48.4 GB (IQ2_S). Longer context needs more: at 32K tokens the KV cache alone adds about 42.9 GB.

NotQuiteAMoE 32B exp i1 is a 158B-parameter Notquiteamoe model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 5 quant files, from 33.2 GB (IQ1_S) to 48.4 GB (IQ2_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S33.2 GB 44.4 GB
Too big Get file →
IQ1_M36.5 GB 47.7 GB
Too big Get file →
IQ2_XXS42.0 GB 53.2 GB
Too big Get file →
IQ2_XS46.6 GB 57.8 GB
Too big Get file →
IQ2_S48.4 GB 59.7 GB
Too big Get file →

What GPU do you need for NotQuiteAMoE 32B exp i1?

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 IQ1_M (36.5 GB file, about 47.7 GB in use).

Which NotQuiteAMoE 32B exp i1 quant should you choose?

IQ2_XXS (42.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 33.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters158B
Layers320
Trained context32,768 tokens
KV cache (fp16)1280 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)81
Last updated2025-07-11

Frequently asked questions about NotQuiteAMoE 32B exp i1

How much VRAM does NotQuiteAMoE 32B exp i1 need?

About 53.2 GB at IQ2_XXS with an 8K context window. That is the 42.0 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 NotQuiteAMoE 32B exp i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NotQuiteAMoE 32B exp i1 GGUF?

It depends on the quant: IQ1_S is 33.2 GB, IQ1_M is 36.5 GB, IQ2_XXS is 42.0 GB, IQ2_XS is 46.6 GB, IQ2_S is 48.4 GB.

What context length does NotQuiteAMoE 32B exp i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 10.7 GB at 8K and 42.9 GB at 32K.

Where can I download NotQuiteAMoE 32B exp i1 GGUF?

The files are on Hugging Face in the mradermacher/NotQuiteAMoE-32B-exp-i1-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 NotQuiteAMoE 32B exp i1 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 mradermacher

All by mradermacher →

Other large models

All large models →