AL

ALMA 7B R

AlmaGGUF by DataSoulUpdated 2025-01-20
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

ALMA 7B R needs about 8.1 GB of memory at Q3_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 12 GB GPU.

ALMA 7B R is a 6.74B-parameter Alma model in GGUF format, quantized by DataSoul. Its trained context length is 4K tokens. The repository has 1 quant file, from 3.3 GB (Q3_K_M) to 3.3 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M3.3 GB 5.9 GB
Fits Get file →

What GPU do you need for ALMA 7B R?

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 Q3_K_M (3.3 GB file, about 8.1 GB in use).

Which ALMA 7B R quant should you choose?

Q3_K_M (3.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byDataSoul
FamilyAlma
Downloads (HF)42
Last updated2025-01-20

Frequently asked questions about ALMA 7B R

How much VRAM does ALMA 7B R need?

About 8.1 GB at Q3_K_M with an 8K context window. That is the 3.3 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 ALMA 7B R on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ALMA 7B R GGUF?

It depends on the quant: Q3_K_M is 3.3 GB.

What context length does ALMA 7B R support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download ALMA 7B R GGUF?

The files are on Hugging Face in the DataSoul/ALMA-7B-R-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 from DataSoul

All by DataSoul →

More Alma models

All Alma →

Other small models

All small models →