LL

st llama 1 5.5b taylor

LlamaGGUF by mradermacherUpdated 2024-11-24
Download on Hugging Face
Parameters5.52B
Context2K
Layers26
Architecturellama
Smallest quant2.1 GB
Quick answer

st llama 1 5.5b taylor needs about 7.3 GB of memory at Q4_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 2.1 GB (Q2_K) to 11.0 GB (F16).

st llama 1 5.5b taylor is a 5.52B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 2K tokens. The repository has 13 quant files, from 2.1 GB (Q2_K) to 11.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 3.5 GB
Fits Get file →
Q3_K_S2.4 GB 3.8 GB
Fits Get file →
Q3_K_M2.7 GB 4.1 GB
Fits Get file →
Q3_K_L3.0 GB 4.3 GB
Fits Get file →
IQ4_XS3.0 GB 4.4 GB
Fits Get file →
Q4_03.1 GB 4.5 GB
Fits Get file →
Q4_K_S3.2 GB 4.5 GB
Fits Get file →
Q4_K_M3.3 GB 4.7 GB
Fits Get file →
Q5_K_S3.8 GB 5.2 GB
Fits Get file →
Q5_K_M3.9 GB 5.3 GB
Fits Get file →
Q6_K4.5 GB 5.9 GB
Fits Get file →
Q8_05.9 GB 7.2 GB
Tight Get file →
F1611.0 GB 12.4 GB
Too big Get file →

What GPU do you need for st llama 1 5.5b taylor?

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 (3.9 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (5.9 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (11.0 GB file, about 15.0 GB in use).

Which st llama 1 5.5b taylor quant should you choose?

Q4_K_M is the usual starting point for st llama 1 5.5b taylor: it balances file size and quality well. Here it is a 3.3 GB file.

The Q8_0 file is 5.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 2.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters5.52B
Layers26
Trained context2,048 tokens
KV cache (fp16)416 KB per token

Source

Quantized bymradermacher
FamilyLlama
Downloads (HF)136
Last updated2024-11-24

Frequently asked questions about st llama 1 5.5b taylor

How much VRAM does st llama 1 5.5b taylor need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 3.3 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 st llama 1 5.5b taylor on an 8 GB GPU?

Yes, with Q5_K_M: the 3.9 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of st llama 1 5.5b taylor GGUF?

It depends on the quant: Q2_K is 2.1 GB, Q3_K_S is 2.4 GB, Q3_K_M is 2.7 GB, Q3_K_L is 3.0 GB, IQ4_XS is 3.0 GB, Q4_0 is 3.1 GB and 7 more.

What context length does st llama 1 5.5b taylor support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.5 GB at 8K and 0.9 GB at 2K.

Where can I download st llama 1 5.5b taylor GGUF?

The files are on Hugging Face in the mradermacher/st-llama-1-5.5b-taylor-GGUF 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 mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →