SA

Salamandra 7b

SalamandraGGUF by ultrawelfareUpdated 2024-12-02
Download on Hugging Face
Parameters7.77B
Context8K
Layers32
Architecturellama
Smallest quant5.6 GB
Quick answer

Salamandra 7b needs about 7.2 GB of memory at Q5_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU.

Salamandra 7b is a 7.77B-parameter Salamandra model in GGUF format, quantized by ultrawelfare. Its trained context length is 8K tokens. The repository has 1 quant file, from 5.6 GB (Q5_K_M) to 5.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.6 GB 7.2 GB
Fits Get file →

What GPU do you need for Salamandra 7b?

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 Q5_K_M (5.6 GB file, about 7.2 GB in use).

Which Salamandra 7b quant should you choose?

Q5_K_M (5.6 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

Architecturellama
Parameters7.77B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byultrawelfare
Licenseapache-2.0
Downloads (HF)19
Last updated2024-12-02

Frequently asked questions about Salamandra 7b

How much VRAM does Salamandra 7b need?

About 7.2 GB at Q5_K_M with an 8K context window. That is the 5.6 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 Salamandra 7b on an 8 GB GPU?

Yes, with Q5_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Salamandra 7b GGUF?

It depends on the quant: Q5_K_M is 5.6 GB.

What context length does Salamandra 7b 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 Salamandra 7b GGUF?

The files are on Hugging Face in the ultrawelfare/salamandra-7b-Q5_K_M-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 Salamandra 7b 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 salamandra-7b

Similar models

Browse all →

More from ultrawelfare

All by ultrawelfare →

More Salamandra models

All Salamandra →

Other small models

All small models →