ZE

zenz v3.1 small

ZenzGGUF by Miwa-KeitaUpdated 2025-08-30
Download on Hugging Face
Parameters95M
Context1K
Layers12
Architecturegpt2
Smallest quant0.1 GB
Quick answer

zenz v3.1 small needs about 0.9 GB of memory at Q5_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.

A compact GPT‑2 based model with 95 million parameters

zenz v3.1 small is a 95 million parameter GPT‑2 style model. It was trained on 1 024 context tokens and released under a CC‑BY‑SA‑4.0 license. The model is available as a single Q5_K_M quantized GGUF file.

Good at

  • Small footprint LLM
  • Fast inference on modest hardware
  • Suitable for lightweight applications

Limits

  • No vision support
  • Limited to 1 024 token context
  • Single quant available

Best for

  • Quick prototyping
  • Edge device inference
  • Text generation in low‑resource settings

Who it’s for. Developers needing a lightweight language model for rapid experimentation or deployment on devices with limited memory. The model is ideal for those who prefer open‑source licensing and minimal resource requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.1 GB 0.6 GB
Fits Get file →

The only available quant is Q5_K_M, file size 0.07 GB. It requires approximately 0.9 GB of VRAM at 8 k context. For 8 GB VRAM, this quant is comfortably within limits. No other quants are provided.

What GPU do you need for zenz v3.1 small?

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 Q5_K_M (0.1 GB file, about 0.9 GB in use).

Which zenz v3.1 small quant should you choose?

Q5_K_M (0.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters95M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized byMiwa-Keita
FamilyZenz
Downloads (HF)624
Last updated2025-08-30

Frequently asked questions about zenz v3.1 small

How much VRAM does zenz v3.1 small need?

About 0.9 GB at Q5_K_M with an 8K context window. That is the 0.1 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 zenz v3.1 small on an 8 GB GPU?

Yes, with Q5_K_M: the 0.1 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of zenz v3.1 small GGUF?

It depends on the quant: Q5_K_M is 0.1 GB.

What context length does zenz v3.1 small support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.

Where can I download zenz v3.1 small GGUF?

The files are on Hugging Face in the Miwa-Keita/zenz-v3.1-small-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 zenz v3.1 small use?

Hugging Face lists the license as cc-by-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q5_K_M quant uses about 0.9 GB of VRAM at 8 k context, well within an 8 GB budget.

What context length does this model support?

It supports up to 1 024 tokens, as trained on that context size.

Is this model suitable for vision tasks?

No, the model has no vision capabilities and is purely text-based.

Similar models

Browse all →

More from Miwa-Keita

All by Miwa-Keita →

More Zenz models

All Zenz →

Other tiny models

All tiny models →