LL

Impish LLAMA 6.84B ARM

LlamaGGUF by SicariusSicariiStuffUpdated 2025-01-09
Download on Hugging Face
Parameters6.84B
Context128K
Layers64
Architecturellama
Smallest quant4.0 GB
Quick answer

Impish LLAMA 6.84B ARM needs about 6.6 GB of memory at Q4_0 (a 4.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.0 GB (Q4_0) to 4.0 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Impish LLAMA 6.84B ARM is a 6.84B-parameter Llama model in GGUF format, quantized by SicariusSicariiStuff. Its trained context length is 128K tokens. The repository has 3 quant files, from 4.0 GB (Q4_0) to 4.0 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →

What GPU do you need for Impish LLAMA 6.84B ARM?

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_0 (4.0 GB file, about 6.6 GB in use).

Which Impish LLAMA 6.84B ARM quant should you choose?

Q4_0 (4.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 4.0 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
Parameters6.84B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

FamilyLlama
Licenseapache-2.0
Downloads (HF)41
Last updated2025-01-09

Frequently asked questions about Impish LLAMA 6.84B ARM

How much VRAM does Impish LLAMA 6.84B ARM need?

About 6.6 GB at Q4_0 with an 8K context window. That is the 4.0 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 Impish LLAMA 6.84B ARM on an 8 GB GPU?

Yes, with Q4_0: the 4.0 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Impish LLAMA 6.84B ARM GGUF?

It depends on the quant: Q4_0 is 4.0 GB, Q4_0 is 4.0 GB, Q4_0 is 4.0 GB.

What context length does Impish LLAMA 6.84B ARM support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Impish LLAMA 6.84B ARM GGUF?

The files are on Hugging Face in the SicariusSicariiStuff/Impish_LLAMA_6.84B_ARM repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Impish LLAMA 6.84B ARM 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 SicariusSicariiStuff

All by SicariusSicariiStuff →

More Llama models

All Llama →

Other small models

All small models →