QW

ZY S2

QwenGGUF by zyr-AGENTUpdated 2026-11-01
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant1.1 GB
Quick answer

ZY S2 needs about 1.9 GB of memory at Q5_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

ZY S2 – 1.5B coding model fine‑tuned for correct Python

ZY S2 is a LoRA fine‑tune of Qwen2.5‑Coder‑1.5B. It focuses on writing correct Python code and runs on a laptop CPU with llama.cpp using the Q5_K_M GGUF format. The model has 1.54B parameters and a full 32,768 token context length.

Good at

  • Python code generation
  • Code reasoning
  • Tool usage

Limits

  • No vision support
  • Not recommended for general conversation
  • Requires CPU for llama.cpp

Best for

  • Local Python coding assistants
  • Educational coding tools
  • Rapid prototyping on laptops

Who it’s for. Developers needing a lightweight, locally deployable code model that excels at Python. Ideal for educational settings, quick prototyping, and developers who prefer CPU‑based inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M1.1 GB 1.9 GB
Fits Get file →

The only available quant is Q5_K_M, file size 1.13 GB. It requires about 1.9 GB of VRAM at 8K context, which is approximate. For lower memory budgets, consider using a different quant if available, but none are listed.

What GPU do you need for ZY S2?

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 (1.1 GB file, about 1.9 GB in use).

Which ZY S2 quant should you choose?

Q5_K_M (1.1 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

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byzyr-AGENT
FamilyQwen
Repositoryzyr-AGENT/ZY-S2
Licenseapache-2.0
Downloads (HF)641
Last updated2026-11-01

Frequently asked questions about ZY S2

How much VRAM does ZY S2 need?

About 1.9 GB at Q5_K_M with an 8K context window. That is the 1.1 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 ZY S2 on an 8 GB GPU?

Yes, with Q5_K_M: the 1.1 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ZY S2 GGUF?

It depends on the quant: Q5_K_M is 1.1 GB.

What context length does ZY S2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download ZY S2 GGUF?

The files are on Hugging Face in the zyr-AGENT/ZY-S2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ZY S2 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.

Can I run ZY S2 on 8 GB VRAM?

Yes, the Q5_K_M quant requires about 1.9 GB of VRAM at 8K context, well within an 8 GB budget.

Does ZY S2 support vision tasks?

No, the model has no vision capabilities.

Is ZY S2 suitable for chat applications?

It is not recommended for general conversation; it is best used for coding tasks.

Other GGUFs of Qwen2.5-Coder-1.5B

Similar models

Browse all →

More from zyr-AGENT

All by zyr-AGENT →

More Qwen models

All Qwen →

Other tiny models

All tiny models →