ZE

zen ingress 1 3b dpo merged

ZenGGUF by ZenithLLMUpdated 2026-09-25
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant1.8 GB
Quick answer

zen ingress 1 3b dpo merged needs about 2.6 GB of memory at IQ4_NL (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.8 GB (IQ4_NL) to 2.2 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

zen ingress 1 3b dpo merged is a 3.09B-parameter Zen model in GGUF format, quantized by ZenithLLM. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.8 GB (IQ4_NL) to 2.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL1.8 GB 2.6 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →

What GPU do you need for zen ingress 1 3b dpo merged?

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 (2.2 GB file, about 3.0 GB in use).

Which zen ingress 1 3b dpo merged quant should you choose?

IQ4_NL (1.8 GB) is the middle option in this repository. 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

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byZenithLLM
FamilyZen
Licenseapache-2.0
Downloads (HF)320
Last updated2026-09-25

Frequently asked questions about zen ingress 1 3b dpo merged

How much VRAM does zen ingress 1 3b dpo merged need?

About 2.6 GB at IQ4_NL with an 8K context window. That is the 1.8 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 zen ingress 1 3b dpo merged on an 8 GB GPU?

Yes, with Q5_K_M: the 2.2 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of zen ingress 1 3b dpo merged GGUF?

It depends on the quant: IQ4_NL is 1.8 GB, Q5_K_M is 2.2 GB.

What context length does zen ingress 1 3b dpo merged support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download zen ingress 1 3b dpo merged GGUF?

The files are on Hugging Face in the ZenithLLM/zen-ingress-1-3b-dpo-merged repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does zen ingress 1 3b dpo merged 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 ZenithLLM

All by ZenithLLM →

More Zen models

All Zen →

Other tiny models

All tiny models →