AL

ALLaM 7B Instruct Preview

AllamGGUF by MaziyarPanahiUpdated 2025-02-21
Download on Hugging Face
Parameters7B
Context4K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

ALLaM 7B Instruct Preview needs about 10.5 GB of memory at Q6_K (a 5.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 4.9 GB (Q5_K_S) to 14.0 GB.

ALLaM 7B Instruct Preview is a 7B-parameter Allam model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 4K tokens. The repository has 5 quant files, from 4.9 GB (Q5_K_S) to 14.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S4.9 GB 7.5 GB
Tight Get file →
Q5_K_M5.0 GB 7.6 GB
Tight Get file →
Q6_K5.7 GB 8.4 GB
Too big Get file →
Q8_07.4 GB 10.1 GB
Too big Get file →
—14.0 GB 16.7 GB
Too big Get file →

What GPU do you need for ALLaM 7B Instruct Preview?

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 Q6_K (5.7 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.4 GB file, about 12.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (14.0 GB file, about 18.8 GB in use).

Which ALLaM 7B Instruct Preview quant should you choose?

Q6_K (5.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_S at 4.9 GB, with the quality trade-offs that come with fewer bits. 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
Parameters7B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byMaziyarPanahi
FamilyAllam
Licenseapache-2.0
Downloads (HF)389
Last updated2025-02-21

Frequently asked questions about ALLaM 7B Instruct Preview

How much VRAM does ALLaM 7B Instruct Preview need?

About 10.5 GB at Q6_K with an 8K context window. That is the 5.7 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 ALLaM 7B Instruct Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ALLaM 7B Instruct Preview GGUF?

It depends on the quant: Q5_K_S is 4.9 GB, Q5_K_M is 5.0 GB, Q6_K is 5.7 GB, Q8_0 is 7.4 GB, file is 14.0 GB.

What context length does ALLaM 7B Instruct Preview 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 ALLaM 7B Instruct Preview GGUF?

The files are on Hugging Face in the MaziyarPanahi/ALLaM-7B-Instruct-preview-reasoning-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ALLaM 7B Instruct Preview 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.

Other GGUFs of ALLaM-7B-Instruct-preview-reasoning

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Allam models

All Allam →

Other small models

All small models →