QW

AVGUR

QwenGGUF by testingusera1Updated 2026-09-30
Download on Hugging Face
Parameters1.9B
Context256K
Layers25
Architectureqwen35
Smallest quant1.6 GB
Quick answer

AVGUR needs about 2.5 GB of memory at Q6_K (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.6 GB (Q6_K) to 2.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

AVGUR – a 1.9B parameter Qwen3.5‑based model for roleplay tasks

AVGUR is a 1.9B parameter causal language model derived from Qwen3.5‑2B. It supports roleplay and is released under the apache‑2.0 license. The model is available in GGUF format with Q6_K quantization.

Good at

  • Roleplay scenarios
  • Text generation
  • Fine‑tuning research

Limits

  • No vision support
  • Limited to 262144 context tokens
  • Requires 2.5 GB VRAM for Q6_K at 8k context

Best for

  • Chatbot prototypes
  • Custom roleplay scripts
  • Research on small‑scale LLMs

Who it’s for. Developers and researchers who need a lightweight Qwen3.5 variant for text‑only applications. The model is suitable for prototyping and task‑specific fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K1.6 GB 2.5 GB
Fits Get file →
—2.1 GB 3.0 GB
Fits Get file →

For 8 GB VRAM, use the Q6_K quantized file (1.61 GB). If more memory is available, the 2.08 GB file provides higher precision. Memory estimates are approximate.

What GPU do you need for AVGUR?

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 the main file (2.1 GB file, about 3.0 GB in use).

Which AVGUR quant should you choose?

Q6_K (1.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.9B
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bytestingusera1
FamilyQwen
Base modelQwen/Qwen3.5-2B
Licenseapache-2.0
Downloads (HF)748
Last updated2026-09-30

Frequently asked questions about AVGUR

How much VRAM does AVGUR need?

About 2.5 GB at Q6_K with an 8K context window. That is the 1.6 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 AVGUR on an 8 GB GPU?

Yes, with the smaller files: the 2.1 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 AVGUR GGUF?

It depends on the quant: Q6_K is 1.6 GB, file is 2.1 GB.

What context length does AVGUR support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download AVGUR GGUF?

The files are on Hugging Face in the testingusera1/AVGUR repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does AVGUR 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 AVGUR on 8 GB VRAM?

Yes, the Q6_K quantized file requires about 2.5 GB VRAM at 8k context, which fits within an 8 GB budget.

Does AVGUR support vision tasks?

No, AVGUR is a text‑only model and does not include vision capabilities.

What license applies to AVGUR?

AVGUR is released under the apache‑2.0 license.

Other GGUFs of Qwen3.5-2B

Similar models

Browse all →

More from testingusera1

All by testingusera1 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →