SE

server

ServerGGUF by doufunao123Updated 2025-02-19
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant15.7 GB
Quick answer

server needs about 17.8 GB of memory at Q8_0 (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 (Q8_0) to 29.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

server is a 14.8B-parameter Server model in GGUF format, quantized by doufunao123. Its trained context length is 128K tokens. The repository has 2 quant files, from 15.7 GB (Q8_0) to 29.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_015.7 GB 17.8 GB
Too big Get file →
F1629.5 GB 31.7 GB
Too big Get file →

What GPU do you need for server?

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 Q8_0 (15.7 GB file, about 17.8 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (29.5 GB file, about 31.7 GB in use).

Which server quant should you choose?

Q8_0 (15.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized bydoufunao123
FamilyServer
Downloads (HF)32
Last updated2025-02-19

Frequently asked questions about server

How much VRAM does server need?

About 17.8 GB at Q8_0 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 server on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of server GGUF?

It depends on the quant: Q8_0 is 15.7 GB, F16 is 29.5 GB.

What context length does server support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 server GGUF?

The files are on Hugging Face in the doufunao123/server 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 doufunao123

All by doufunao123 →

More Server models

All Server →

Other medium models

All medium models →