AR

aranea ancilla 116b v1.0

AraneaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters117B
Context32K
Layers136
Architecturellama
Smallest quant42.9 GB
Quick answer

aranea ancilla 116b v1.0 needs about 48.0 GB of memory at Q2_K (a 42.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 42.9 GB (Q2_K) to 47.8 GB (IQ3_XS).

aranea ancilla 116b v1.0 is a 117B-parameter Aranea model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 2 quant files, from 42.9 GB (Q2_K) to 47.8 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K42.9 GB 48.0 GB
Too big Get file →
IQ3_XS47.8 GB 52.8 GB
Too big Get file →

What GPU do you need for aranea ancilla 116b v1.0?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K (42.9 GB file, about 48.0 GB in use).

Which aranea ancilla 116b v1.0 quant should you choose?

Q2_K (42.9 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters117B
Layers136
Trained context32,764 tokens
KV cache (fp16)544 KB per token

Source

Quantized bymradermacher
FamilyAranea
Downloads (HF)27
Last updated2024-05-06

Frequently asked questions about aranea ancilla 116b v1.0

How much VRAM does aranea ancilla 116b v1.0 need?

About 48.0 GB at Q2_K with an 8K context window. That is the 42.9 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 aranea ancilla 116b v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of aranea ancilla 116b v1.0 GGUF?

It depends on the quant: Q2_K is 42.9 GB, IQ3_XS is 47.8 GB.

What context length does aranea ancilla 116b v1.0 support?

The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 4.6 GB at 8K and 18.3 GB at 32K.

Where can I download aranea ancilla 116b v1.0 GGUF?

The files are on Hugging Face in the mradermacher/aranea-ancilla-116b-v1.0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of aranea-ancilla-116b-v1.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aranea models

All Aranea →

Other large models

All large models →