SU

SummLlama3 8B Q3 K M

SummllamaGGUF by dil99xUpdated 2024-11-21
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.0 GB
Quick answer

SummLlama3 8B Q3 K M needs about 5.6 GB of memory at Q3_K_M (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU.

SummLlama3 8B Q3 K M is a 8.03B-parameter Summllama model in GGUF format, quantized by dil99x. Its trained context length is 8K tokens. The repository has 1 quant file, from 4.0 GB (Q3_K_M) to 4.0 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M4.0 GB (2 parts) 5.6 GB
Fits Get file →

What GPU do you need for SummLlama3 8B Q3 K M?

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: the best quant that fits is Q3_K_M (4.0 GB file, about 5.6 GB in use).

Which SummLlama3 8B Q3 K M quant should you choose?

Q3_K_M (4.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydil99x
FamilySummllama
Downloads (HF)24
Last updated2024-11-21

Frequently asked questions about SummLlama3 8B Q3 K M

How much VRAM does SummLlama3 8B Q3 K M need?

About 5.6 GB at Q3_K_M with an 8K context window. That is the 4.0 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 SummLlama3 8B Q3 K M on an 8 GB GPU?

Yes, with Q3_K_M: the 4.0 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SummLlama3 8B Q3 K M GGUF?

It depends on the quant: Q3_K_M is 4.0 GB.

What context length does SummLlama3 8B Q3 K M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download SummLlama3 8B Q3 K M GGUF?

The files are on Hugging Face in the dil99x/SummLlama3-8B-Q3_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of SummLlama3-8B

Similar models

Browse all →

More from dil99x

All by dil99x →

More Summllama models

All Summllama →

Other small models

All small models →