QW

Qwen3-14B

QwenGGUF by kolosalUpdated 2025-04-29
Download on Hugging Face
Parameters14.8B
Context40K
Layers40
Architectureqwen3
Smallest quant9.2 GB
Quick answer

Qwen3-14B needs about 20.6 GB of memory at Q8_K_XL (a 18.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 9.2 GB (Q4_K_XL) to 29.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Qwen3-14B is a 14.8B-parameter Qwen model in GGUF format, quantized by kolosal. Its trained context length is 40K tokens. The repository has 3 quant files, from 9.2 GB (Q4_K_XL) to 29.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_XL9.2 GB 11.0 GB
Too big Get file →
Q8_K_XL18.8 GB 20.6 GB
Too big Get file →
BF1629.5 GB 31.4 GB
Too big Get file →

What GPU do you need for Qwen3-14B?

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: the best quant that fits is Q4_K_XL (9.2 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_XL (9.2 GB file, about 11.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_K_XL (18.8 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (29.5 GB file, about 31.4 GB in use).

Which Qwen3-14B quant should you choose?

Q8_K_XL (18.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_K_XL at 9.2 GB, with the quality trade-offs that come with fewer bits. 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

Architectureqwen3
Parameters14.8B
Layers40
Trained context40,960 tokens
KV cache (fp16)160 KB per token

Source

Quantized bykolosal
FamilyQwen
Downloads (HF)6
Last updated2025-04-29

Frequently asked questions about Qwen3-14B

How much VRAM does Qwen3-14B need?

About 20.6 GB at Q8_K_XL with an 8K context window. That is the 18.8 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 Qwen3-14B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3-14B GGUF?

It depends on the quant: Q4_K_XL is 9.2 GB, Q8_K_XL is 18.8 GB, BF16 is 29.5 GB.

What context length does Qwen3-14B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Qwen3-14B GGUF?

The files are on Hugging Face in the kolosal/qwen3-14b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from kolosal

All by kolosal →

More Qwen models

All Qwen →

Other medium models

All medium models →