NE

NeuralBeagle-11B

NeuralbeagleGGUF by s3nhUpdated 2024-01-20
Download on Hugging Face
Parameters10.7B
Context32K
Layers48
Architecturellama
Smallest quant4.7 GB
Quick answer

NeuralBeagle-11B needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 4.7 GB (Q3_K_S) to 11.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

NeuralBeagle-11B is a 10.7B-parameter Neuralbeagle model in GGUF format, quantized by s3nh. Its trained context length is 32K tokens. The repository has 5 quant files, from 4.7 GB (Q3_K_S) to 11.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S4.7 GB 6.8 GB
Fits Get file →
Q4_K_M6.5 GB 8.6 GB
Too big Get file →
Q5_K_M7.6 GB 9.7 GB
Too big Get file →
Q6_K8.8 GB 10.9 GB
Too big Get file →
Q8_011.4 GB 13.5 GB
Too big Get file →

What GPU do you need for NeuralBeagle-11B?

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: the best quant that fits is Q3_K_S (4.7 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which NeuralBeagle-11B quant should you choose?

Q4_K_M is the usual starting point for NeuralBeagle-11B: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 4.7 GB, with the quality trade-offs that come with fewer bits. 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
Parameters10.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bys3nh
Licenseopenrail
Downloads (HF)27
Last updated2024-01-20

Frequently asked questions about NeuralBeagle-11B

How much VRAM does NeuralBeagle-11B need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 NeuralBeagle-11B on an 8 GB GPU?

Yes, with Q3_K_S: the 4.7 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NeuralBeagle-11B GGUF?

It depends on the quant: Q3_K_S is 4.7 GB, Q4_K_M is 6.5 GB, Q5_K_M is 7.6 GB, Q6_K is 8.8 GB, Q8_0 is 11.4 GB.

What context length does NeuralBeagle-11B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download NeuralBeagle-11B GGUF?

The files are on Hugging Face in the s3nh/NeuralBeagle-11B-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 NeuralBeagle-11B use?

Hugging Face lists the license as openrail. 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 s3nh

All by s3nh →

More Neuralbeagle models

All Neuralbeagle →

Other medium models

All medium models →