HE

Heimer dpo TinyLlama 1.1B

HeimerGGUF by BenjamintuUpdated 2024-02-03
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.8 GB
Quick answer

Heimer dpo TinyLlama 1.1B needs about 1.5 GB of memory at Q5_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Heimer dpo TinyLlama 1.1B is a 1.1B-parameter Heimer model in GGUF format, quantized by Benjamintu. Its trained context length is 2K tokens. The repository has 1 quant file, from 0.8 GB (Q5_K_M) to 0.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.8 GB 1.3 GB
Fits Get file →

What GPU do you need for Heimer dpo TinyLlama 1.1B?

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 Q5_K_M (0.8 GB file, about 1.5 GB in use).

Which Heimer dpo TinyLlama 1.1B quant should you choose?

Q5_K_M (0.8 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
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byBenjamintu
FamilyHeimer
Downloads (HF)4
Last updated2024-02-03

Frequently asked questions about Heimer dpo TinyLlama 1.1B

How much VRAM does Heimer dpo TinyLlama 1.1B need?

About 1.5 GB at Q5_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 Heimer dpo TinyLlama 1.1B on an 8 GB GPU?

Yes, with Q5_K_M: the 0.8 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Heimer dpo TinyLlama 1.1B GGUF?

It depends on the quant: Q5_K_M is 0.8 GB.

What context length does Heimer dpo TinyLlama 1.1B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download Heimer dpo TinyLlama 1.1B GGUF?

The files are on Hugging Face in the Benjamintu/Heimer-dpo-TinyLlama-1.1B-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 Heimer models

All Heimer →

Other tiny models

All tiny models →