UN

Underdog 27B 1.1

UnderdogGGUF by ConwayResearchUpdated 2026-10-04
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant16.9 GB
Quick answer

Underdog 27B 1.1 needs about 19.6 GB of memory at Q4_1 (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Underdog 27B 1.1 – 27‑billion‑parameter assistant for conversation, coding, and summarization

Underdog 27B 1.1 is a 26.9‑billion‑parameter model based on the qwen35 architecture. It supports reasoning and tool usage. The model is available in a 4‑bit GGUF format for local inference.

Good at

  • Reasoning
  • Tool usage
  • Conversational writing

Limits

  • No vision support
  • Large context 262144 tokens
  • Requires 19.6 GB VRAM for 8 k context

Best for

  • Local code generation
  • Summarizing long documents
  • Interactive chat

Who it’s for. Developers and researchers who need a powerful local assistant for text generation and coding tasks. The model is suitable for users with sufficient GPU memory to run the 4‑bit GGUF file.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_116.9 GB 19.6 GB
Too big Get file →

The only available quantization is Q4_1, with a file size of 16.91 GB and an estimated memory usage of 19.6 GB at 8 k context. This is suitable for GPUs with at least 20 GB VRAM. For lower memory budgets, no other quantizations are provided.

What GPU do you need for Underdog 27B 1.1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_1 (16.9 GB file, about 19.6 GB in use).

Which Underdog 27B 1.1 quant should you choose?

Q4_1 (16.9 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

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byConwayResearch
FamilyUnderdog
Licenseapache-2.0
Downloads (HF)650
Last updated2026-10-04

Frequently asked questions about Underdog 27B 1.1

How much VRAM does Underdog 27B 1.1 need?

About 19.6 GB at Q4_1 with an 8K context window. That is the 16.9 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 Underdog 27B 1.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Underdog 27B 1.1 GGUF?

It depends on the quant: Q4_1 is 16.9 GB.

What context length does Underdog 27B 1.1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Underdog 27B 1.1 GGUF?

The files are on Hugging Face in the ConwayResearch/Underdog-27B-1.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Underdog 27B 1.1 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 Underdog 27B 1.1 on a GPU with 8 GB VRAM?

No. The Q4_1 quantization requires approximately 19.6 GB VRAM at 8 k context, which exceeds 8 GB.

Does the model support image input?

No. The model has no vision capabilities.

What is the maximum context length I can use?

The model was trained with 262144 tokens, which is the maximum context length.

Similar models

Browse all →

More from ConwayResearch

All by ConwayResearch →

More Underdog models

All Underdog →

Other medium models

All medium models →