SA

saiga tlite 8b abliterated

SaigaGGUF by AndreyRGWUpdated 2024-07-29
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.7 GB
Quick answer

saiga tlite 8b abliterated needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.7 GB (IQ4_NL) to 4.9 GB (Q4_K_M).

saiga tlite 8b abliterated is a 8.03B-parameter Saiga model in GGUF format, quantized by AndreyRGW. Its trained context length is 8K tokens. The repository has 2 quant files, from 4.7 GB (IQ4_NL) to 4.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →

What GPU do you need for saiga tlite 8b abliterated?

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 Q4_K_M (4.9 GB file, about 6.5 GB in use).

Which saiga tlite 8b abliterated quant should you choose?

Q4_K_M is the usual starting point for saiga tlite 8b abliterated: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ4_NL at 4.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 byAndreyRGW
FamilySaiga
Downloads (HF)15
Last updated2024-07-29

Frequently asked questions about saiga tlite 8b abliterated

How much VRAM does saiga tlite 8b abliterated need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 saiga tlite 8b abliterated on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of saiga tlite 8b abliterated GGUF?

It depends on the quant: IQ4_NL is 4.7 GB, Q4_K_M is 4.9 GB.

What context length does saiga tlite 8b abliterated 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 saiga tlite 8b abliterated GGUF?

The files are on Hugging Face in the AndreyRGW/saiga_tlite_8b_abliterated_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 AndreyRGW

All by AndreyRGW →

More Saiga models

All Saiga →

Other small models

All small models →