CS

CSTinyLlama 1.2B

CstinyllamaGGUF by BUT-FITUpdated 2025-01-07
Download on Hugging Face
Parameters1.23B
Context16K
Layers22
Architecturellama
Smallest quant1.3 GB
Quick answer

CSTinyLlama 1.2B needs about 3.1 GB of memory at BF16 (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.3 GB (Q8_0) to 4.9 GB (F32).

CSTinyLlama 1.2B is a 1.23B-parameter Cstinyllama model in GGUF format, quantized by BUT-FIT. Its trained context length is 16K tokens. The repository has 3 quant files, from 1.3 GB (Q8_0) to 4.9 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.3 GB 2.0 GB
Fits Get file →
BF162.5 GB 3.1 GB
Fits Get file →
F324.9 GB 5.6 GB
Fits Get file →

What GPU do you need for CSTinyLlama 1.2B?

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 BF16 (2.5 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (4.9 GB file, about 5.6 GB in use).

Which CSTinyLlama 1.2B quant should you choose?

BF16 (2.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is Q8_0 at 1.3 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.23B
Layers22
Trained context16,384 tokens
KV cache (fp16)22 KB per token

Source

Quantized byBUT-FIT
Downloads (HF)60
Last updated2025-01-07

Frequently asked questions about CSTinyLlama 1.2B

How much VRAM does CSTinyLlama 1.2B need?

About 3.1 GB at BF16 with an 8K context window. That is the 2.5 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 CSTinyLlama 1.2B on an 8 GB GPU?

Yes, with F32: the 4.9 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 CSTinyLlama 1.2B GGUF?

It depends on the quant: Q8_0 is 1.3 GB, BF16 is 2.5 GB, F32 is 4.9 GB.

What context length does CSTinyLlama 1.2B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.4 GB at 16K.

Where can I download CSTinyLlama 1.2B GGUF?

The files are on Hugging Face in the BUT-FIT/CSTinyLLama-1.2B-RAGsum 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 BUT-FIT

All by BUT-FIT →

Other tiny models

All tiny models →