QW

quill 1 preview

QwenGGUF by minsoreUpdated 2026-09-25
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.4 GB
Quick answer

quill 1 preview needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q4_K_M) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Quill 1 Preview: lightweight FIM autocomplete for Python

Quill 1 Preview is a 0.5B parameter code-completion model built on Qwen2.5-Coder-0.5B. It is tuned for Fill-in-the-Middle tasks in IDEs and runs comfortably on consumer hardware. The model is licensed under Apache 2.0.

Good at

  • Fill-in-the-Middle autocomplete
  • Python code completion
  • Real‑time editor integration

Limits

  • No chat functionality
  • 1024 token context
  • Python‑only
  • May append tests or repeat integers

Best for

  • IDE autocomplete
  • Live code suggestions
  • Python scripting

Who it’s for. Developers looking for a fast, lightweight autocomplete model for Python. It is ideal for users who need real‑time suggestions without the overhead of a full chat model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

For 2 GB VRAM, use the Q4_K_M quant (0.4 GB file, ~1 GB memory at 8 k context). If more memory is available, the F16 quant (0.99 GB file, ~1.6 GB memory at 8 k context) offers higher precision.

What GPU do you need for quill 1 preview?

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 F16 (1.0 GB file, about 1.6 GB in use).

Which quill 1 preview quant should you choose?

Q4_K_M is the usual starting point for quill 1 preview: it balances file size and quality well. Here it is a 0.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized byminsore
FamilyQwen
Licenseapache-2.0
Downloads (HF)710
Last updated2026-09-25

Frequently asked questions about quill 1 preview

How much VRAM does quill 1 preview need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 quill 1 preview on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quill 1 preview GGUF?

It depends on the quant: Q4_K_M is 0.4 GB, F16 is 1.0 GB.

What context length does quill 1 preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download quill 1 preview GGUF?

The files are on Hugging Face in the minsore/quill-1-preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does quill 1 preview 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 Quill 1 Preview on 2 GB VRAM?

Yes, the Q4_K_M quant requires only 0.4 GB file size and about 1 GB VRAM at 8 k context, fitting within 2 GB.

Does Quill support other programming languages?

No, it is trained exclusively on Python FIM data and is best used for Python code.

Can Quill be used for chat?

No, the model is purpose‑built for autocomplete and does not function as a chat assistant.

Other GGUFs of Qwen2.5-Coder-0.5B-Instruct

Similar models

Browse all →

More from minsore

All by minsore →

More Qwen models

All Qwen →

Other tiny models

All tiny models →