LO

fd lora merged 64x128 Q5 0

LoraGGUF by ehristoforuUpdated 2025-02-02
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant1.3 GB
Quick answer

fd lora merged 64x128 Q5 0 needs about 2.0 GB of memory at Q5_0 (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

fd lora merged 64x128 Q5 0 is a 1.78B-parameter Lora model in GGUF format, quantized by ehristoforu. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.3 GB (Q5_0) to 1.3 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_01.3 GB 2.0 GB
Fits Get file →

What GPU do you need for fd lora merged 64x128 Q5 0?

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: the best quant that fits is Q5_0 (1.3 GB file, about 2.0 GB in use).

Which fd lora merged 64x128 Q5 0 quant should you choose?

Q5_0 (1.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized byehristoforu
FamilyLora
Licensemit
Downloads (HF)24
Last updated2025-02-02

Frequently asked questions about fd lora merged 64x128 Q5 0

How much VRAM does fd lora merged 64x128 Q5 0 need?

About 2.0 GB at Q5_0 with an 8K context window. That is the 1.3 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 fd lora merged 64x128 Q5 0 on an 8 GB GPU?

Yes, with Q5_0: the 1.3 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of fd lora merged 64x128 Q5 0 GGUF?

It depends on the quant: Q5_0 is 1.3 GB.

What context length does fd lora merged 64x128 Q5 0 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download fd lora merged 64x128 Q5 0 GGUF?

The files are on Hugging Face in the ehristoforu/fd-lora-merged-64x128-Q5_0-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 fd lora merged 64x128 Q5 0 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ehristoforu

All by ehristoforu →

More Lora models

All Lora →

Other tiny models

All tiny models →