AM

ama3

AmaGGUF by kuuhaku06Updated 2024-11-06
Download on Hugging Face
Parameters10.8B
Context4K
Layers48
Architecturellama
Smallest quant7.7 GB
Quick answer

ama3 needs about 9.8 GB of memory at Q5_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU.

ama3 is a 10.8B-parameter Ama model in GGUF format, quantized by kuuhaku06. Its trained context length is 4K tokens. The repository has 1 quant file, from 7.7 GB (Q5_K_M) to 7.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M7.7 GB 9.0 GB
Too big Get file →

What GPU do you need for ama3?

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: the best quant that fits is Q5_K_M (7.7 GB file, about 9.8 GB in use).

Which ama3 quant should you choose?

Q5_K_M (7.7 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
Parameters10.8B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bykuuhaku06
FamilyAma
Repositorykuuhaku06/ama3
Downloads (HF)4
Last updated2024-11-06

Frequently asked questions about ama3

How much VRAM does ama3 need?

About 9.8 GB at Q5_K_M with an 8K context window. That is the 7.7 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 ama3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ama3 GGUF?

It depends on the quant: Q5_K_M is 7.7 GB.

What context length does ama3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download ama3 GGUF?

The files are on Hugging Face in the kuuhaku06/ama3 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 kuuhaku06

All by kuuhaku06 →

Other medium models

All medium models →