ML

mlabonne NeuralPipe 7B ties

MlabonneGGUF by RichardErkhovUpdated 2024-07-27
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

mlabonne NeuralPipe 7B ties needs about 4.8 GB of memory at IQ3_S (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 2.7 GB (Q2_K) to 3.5 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mlabonne NeuralPipe 7B ties is a 7.24B-parameter Mlabonne model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 7 quant files, from 2.7 GB (Q2_K) to 3.5 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K3.5 GB 5.1 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →

What GPU do you need for mlabonne NeuralPipe 7B ties?

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: the best quant that fits is Q3_K (3.5 GB file, about 5.1 GB in use).

Which mlabonne NeuralPipe 7B ties quant should you choose?

IQ3_S (3.2 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.

If memory is tight, the smallest file is Q2_K at 2.7 GB, with the quality trade-offs that come with fewer bits. 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMlabonne
Licenseapache-2.0
Downloads (HF)5
Last updated2024-07-27

Frequently asked questions about mlabonne NeuralPipe 7B ties

How much VRAM does mlabonne NeuralPipe 7B ties need?

About 4.8 GB at IQ3_S with an 8K context window. That is the 3.2 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 mlabonne NeuralPipe 7B ties on an 8 GB GPU?

Yes, with Q3_K: the 3.5 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mlabonne NeuralPipe 7B ties GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K is 3.5 GB and 1 more.

What context length does mlabonne NeuralPipe 7B ties support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download mlabonne NeuralPipe 7B ties GGUF?

The files are on Hugging Face in the RichardErkhov/mlabonne_-_NeuralPipe-7B-ties-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 mlabonne NeuralPipe 7B ties 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mlabonne models

All Mlabonne →

Other small models

All small models →