QW

Qwable 27B

QwableGGUF by poisonxaUpdated 2026-10-12
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant15.7 GB
Quick answer

Qwable 27B needs about 18.4 GB of memory at MXFP4 (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.7 GB (MXFP4) to 15.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Qwable 27B – a 27.3B parameter dense hybrid model

Qwable 27B is a 27.3B parameter dense hybrid model based on the qwen35 architecture. It supports reasoning and tool usage. The model is released under the apache-2.0 license.

Good at

  • reasoning
  • tools
  • large context

Limits

  • no vision support
  • trained context 262144 tokens
  • no mixture of experts

Best for

  • complex reasoning tasks
  • tool‑integrated workflows
  • long‑form content generation

Who it’s for. Developers and researchers needing a large dense model for reasoning and tool integration. The model is suitable for applications that require a 262144 token context window and do not need vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP415.7 GB 18.4 GB
Too big Get file →
—15.7 GB 18.4 GB
Too big Get file →

For 8 GB VRAM use the MXFP4 quant file (15.67 GB, ~18.4 GB memory at 8 k context). For larger VRAM budgets the unknown quant file is identical in size and memory usage. Memory estimates are approximate.

What GPU do you need for Qwable 27B?

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 the main file (15.7 GB file, about 18.4 GB in use).

Which Qwable 27B quant should you choose?

MXFP4 (15.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized bypoisonxa
FamilyQwable
Licenseapache-2.0
Downloads (HF)720
Last updated2026-10-12

Frequently asked questions about Qwable 27B

How much VRAM does Qwable 27B need?

About 18.4 GB at MXFP4 with an 8K context window. That is the 15.7 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 Qwable 27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwable 27B GGUF?

It depends on the quant: MXFP4 is 15.7 GB, file is 15.7 GB.

What context length does Qwable 27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Qwable 27B GGUF?

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

What license does Qwable 27B 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 Qwable 27B on 8 GB VRAM?

Yes, using the MXFP4 quant file requires about 18.4 GB memory at 8 k context, which is beyond 8 GB VRAM. A smaller VRAM device would need a lower‑bit quant or a different model.

Does Qwable 27B support vision?

No, the model has no vision capabilities.

What license is Qwable 27B released under?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from poisonxa

All by poisonxa →

More Qwable models

All Qwable →

Other medium models

All medium models →