BE

Bepis 9B GGUF IQ Imatrix

BepisGGUF by LewdiculousUpdated 2024-03-04
Download on Hugging Face
Parameters8.99B
Context32K
Layers40
Architecturellama
Smallest quant3.5 GB
Quick answer

Bepis 9B GGUF IQ Imatrix needs about 7.3 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 13 quants, from 3.5 GB (IQ3_XXS) to 18.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Bepis 9B GGUF IQ Imatrix is a 8.99B-parameter Bepis model in GGUF format, quantized by Lewdiculous. Its trained context length is 32K tokens. The repository has 13 quant files, from 3.5 GB (IQ3_XXS) to 18.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS3.5 GB 5.3 GB
Fits Get file →
IQ3_XS3.7 GB 5.6 GB
Fits Get file →
IQ3_S3.9 GB 5.8 GB
Fits Get file →
IQ3_M4.1 GB 5.9 GB
Fits Get file →
IQ4_XS4.8 GB 6.7 GB
Fits Get file →
IQ4_NL5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.1 GB 7.0 GB
Fits Get file →
Q4_K_M5.4 GB 7.3 GB
Tight Get file →
Q5_K_S6.2 GB 8.0 GB
Too big Get file →
Q5_K_M6.4 GB 8.2 GB
Too big Get file →
Q6_K7.4 GB 9.2 GB
Too big Get file →
Q8_09.6 GB 11.4 GB
Too big Get file →
F1618.0 GB 19.8 GB
Too big Get file →

What GPU do you need for Bepis 9B GGUF IQ Imatrix?

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 IQ3_M (4.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (18.0 GB file, about 19.8 GB in use).

Which Bepis 9B GGUF IQ Imatrix quant should you choose?

Q4_K_M is the usual starting point for Bepis 9B GGUF IQ Imatrix: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 9.6 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 IQ3_XXS at 3.5 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
Parameters8.99B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byLewdiculous
FamilyBepis
Downloads (HF)213
Last updated2024-03-04

Frequently asked questions about Bepis 9B GGUF IQ Imatrix

How much VRAM does Bepis 9B GGUF IQ Imatrix need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Bepis 9B GGUF IQ Imatrix on an 8 GB GPU?

Yes, with Q5_K_S: the 6.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bepis 9B GGUF IQ Imatrix GGUF?

It depends on the quant: IQ3_XXS is 3.5 GB, IQ3_XS is 3.7 GB, IQ3_S is 3.9 GB, IQ3_M is 4.1 GB, IQ4_XS is 4.8 GB, IQ4_NL is 5.1 GB and 7 more.

What context length does Bepis 9B GGUF IQ Imatrix support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Bepis 9B GGUF IQ Imatrix GGUF?

The files are on Hugging Face in the Lewdiculous/Bepis_9B-GGUF-IQ-Imatrix 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 Lewdiculous

All by Lewdiculous →

More Bepis models

All Bepis →

Other small models

All small models →