BA

BADMISTRAL 1.5B

BadmistralGGUF by MaziyarPanahiUpdated 2024-10-31
Download on Hugging Face
Parameters1.55B
Context8K
Layers20
Architecturellama
Smallest quant1.1 GB
Quick answer

BADMISTRAL 1.5B needs about 2.2 GB of memory at Q6_K (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.1 GB (Q5_K_S) to 3.1 GB.

BADMISTRAL 1.5B is a 1.55B-parameter Badmistral model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 8K tokens. The repository has 5 quant files, from 1.1 GB (Q5_K_S) to 3.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S1.1 GB 2.0 GB
Fits Get file →
Q5_K_M1.1 GB 2.0 GB
Fits Get file →
Q6_K1.3 GB 2.2 GB
Fits Get file →
Q8_01.7 GB 2.6 GB
Fits Get file →
—3.1 GB 4.0 GB
Fits Get file →

What GPU do you need for BADMISTRAL 1.5B?

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: the best quant that fits is the main file (3.1 GB file, about 4.0 GB in use).

Which BADMISTRAL 1.5B quant should you choose?

Q6_K (1.3 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 1.1 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
Parameters1.55B
Layers20
Trained context8,192 tokens
KV cache (fp16)50 KB per token

Source

Quantized byMaziyarPanahi
Licenseapache-2.0
Downloads (HF)96
Last updated2024-10-31

Frequently asked questions about BADMISTRAL 1.5B

How much VRAM does BADMISTRAL 1.5B need?

About 2.2 GB at Q6_K with an 8K context window. That is the 1.3 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 BADMISTRAL 1.5B on an 8 GB GPU?

Yes, with the smaller files: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BADMISTRAL 1.5B GGUF?

It depends on the quant: Q5_K_S is 1.1 GB, Q5_K_M is 1.1 GB, Q6_K is 1.3 GB, Q8_0 is 1.7 GB, file is 3.1 GB.

What context length does BADMISTRAL 1.5B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.4 GB at 8K.

Where can I download BADMISTRAL 1.5B GGUF?

The files are on Hugging Face in the MaziyarPanahi/BADMISTRAL-1.5B-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 BADMISTRAL 1.5B 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 BADMISTRAL-1.5B

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Badmistral models

All Badmistral →

Other tiny models

All tiny models →