GG

ggml model f32

GgmlGGUF by zmarcusssUpdated 2024-11-13
Download on Hugging Face
Parameters1.36B
Context2K
Layers24
Architecturellama
Smallest quant5.5 GB
Quick answer

ggml model f32 needs about 7.6 GB of memory at F32 (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU.

ggml model f32 is a 1.36B-parameter Ggml model in GGUF format, quantized by zmarcusss. Its trained context length is 2K tokens. The repository has 1 quant file, from 5.5 GB (F32) to 5.5 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F325.5 GB 6.4 GB
Fits Get file →

What GPU do you need for ggml model f32?

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: the best quant that fits is F32 (5.5 GB file, about 7.6 GB in use).

Which ggml model f32 quant should you choose?

F32 (5.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.36B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized byzmarcusss
FamilyGgml
Licenseapache-2.0
Downloads (HF)16
Last updated2024-11-13

Frequently asked questions about ggml model f32

How much VRAM does ggml model f32 need?

About 7.6 GB at F32 with an 8K context window. That is the 5.5 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 ggml model f32 on an 8 GB GPU?

Yes, with F32: the 5.5 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ggml model f32 GGUF?

It depends on the quant: F32 is 5.5 GB.

What context length does ggml model f32 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download ggml model f32 GGUF?

The files are on Hugging Face in the zmarcusss/ggml-model-f32 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ggml model f32 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.

Similar models

Browse all →

More Ggml models

All Ggml →

Other tiny models

All tiny models →