IS

iSA 02 1B NoTags Preview

IsaGGUF by NeuraLakeAiUpdated 2025-01-26
Download on Hugging Face
Parameters1.24B
Context256K
Layers16
Architecturellama
Smallest quant0.8 GB
Quick answer

iSA 02 1B NoTags Preview needs about 1.6 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.8 GB (Q4_0) to 5.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

iSA 02 1B NoTags Preview is a 1.24B-parameter Isa model in GGUF format, quantized by NeuraLakeAi. Its trained context length is 256K tokens. The repository has 10 quant files, from 0.8 GB (Q4_0) to 5.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_K_M0.8 GB 1.6 GB
Fits Get file →
Q4_10.8 GB 1.6 GB
Fits Get file →
Q5_00.9 GB 1.7 GB
Fits Get file →
Q5_K_M0.9 GB 1.7 GB
Fits Get file →
Q5_11.0 GB 1.7 GB
Fits Get file →
Q6_K1.0 GB 1.8 GB
Fits Get file →
Q8_01.3 GB 2.1 GB
Fits Get file →
F162.5 GB 3.2 GB
Fits Get file →
F325.0 GB 5.7 GB
Fits Get file →

What GPU do you need for iSA 02 1B NoTags Preview?

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: the best quant that fits is F16 (2.5 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (5.0 GB file, about 5.7 GB in use).

Which iSA 02 1B NoTags Preview quant should you choose?

Q4_K_M is the usual starting point for iSA 02 1B NoTags Preview: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.3 GB, about 1.6 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 Q4_0 at 0.8 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
Parameters1.24B
Layers16
Trained context262,144 tokens
KV cache (fp16)32 KB per token

Source

Quantized byNeuraLakeAi
FamilyIsa
Licenseapache-2.0
Downloads (HF)241
Last updated2025-01-26

Frequently asked questions about iSA 02 1B NoTags Preview

How much VRAM does iSA 02 1B NoTags Preview need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.8 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 iSA 02 1B NoTags Preview on an 8 GB GPU?

Yes, with F32: the 5.0 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of iSA 02 1B NoTags Preview GGUF?

It depends on the quant: Q4_0 is 0.8 GB, Q4_K_M is 0.8 GB, Q4_1 is 0.8 GB, Q5_0 is 0.9 GB, Q5_K_M is 0.9 GB, Q5_1 is 1.0 GB and 4 more.

What context length does iSA 02 1B NoTags Preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download iSA 02 1B NoTags Preview GGUF?

The files are on Hugging Face in the NeuraLakeAi/iSA-02-1B-NoTags-Preview repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does iSA 02 1B NoTags Preview 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 from NeuraLakeAi

All by NeuraLakeAi →

More Isa models

All Isa →

Other tiny models

All tiny models →