QW

NQLSG Qwen2.5 14B MegaFusion v6

QwenGGUF by LunzimaUpdated 2025-02-24
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant8.4 GB
Quick answer

NQLSG Qwen2.5 14B MegaFusion v6 needs about 10.5 GB of memory at its main file (a 8.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.4 GB to 9.7 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

NQLSG Qwen2.5 14B MegaFusion v6 is a 14.8B-parameter Qwen model in GGUF format, quantized by Lunzima. Its trained context length is 32K tokens. The repository has 2 quant files, from 8.4 GB to 9.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.4 GB 10.5 GB
Too big Get file →
Q5_K_M9.7 GB 11.8 GB
Too big Get file →

What GPU do you need for NQLSG Qwen2.5 14B MegaFusion v6?

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 Q5_K_M (9.7 GB file, about 11.8 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byLunzima
FamilyQwen
Licenseapache-2.0
Downloads (HF)28
Last updated2025-02-24

Frequently asked questions about NQLSG Qwen2.5 14B MegaFusion v6

How much VRAM does NQLSG Qwen2.5 14B MegaFusion v6 need?

About 10.5 GB at its main file with an 8K context window. That is the 8.4 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 NQLSG Qwen2.5 14B MegaFusion v6 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NQLSG Qwen2.5 14B MegaFusion v6 GGUF?

It depends on the quant: file is 8.4 GB, Q5_K_M is 9.7 GB.

What context length does NQLSG Qwen2.5 14B MegaFusion v6 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download NQLSG Qwen2.5 14B MegaFusion v6 GGUF?

The files are on Hugging Face in the Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v6-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 NQLSG Qwen2.5 14B MegaFusion v6 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.

Other GGUFs of NQLSG-Qwen2.5-14B-MegaFusion-v6

Similar models

Browse all →

More from Lunzima

All by Lunzima →

More Qwen models

All Qwen →

Other medium models

All medium models →