KA

Katayoon VPO SELM Zephyr 7B iter 2

KatayoonGGUF by RichardErkhovUpdated 2024-08-03
Download on Hugging Face
Parameters7.24B
Context32K
Layers—
Architecturellama
Smallest quant0.1 GB
Quick answer

Katayoon VPO SELM Zephyr 7B iter 2 needs about 2.2 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.1 GB (Q8_0) to 4.3 GB (Q5_K).

Katayoon VPO SELM Zephyr 7B iter 2 is a 7.24B-parameter Katayoon model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 0.1 GB (Q8_0) to 4.3 GB (Q5_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.8 GB
Fits Get file →
Q5_10.2 GB 0.8 GB
Fits Get file →
Q4_10.7 GB 1.2 GB
Fits Get file →
Q5_K_M1.0 GB 1.6 GB
Fits Get file →
Q5_01.4 GB 2.1 GB
Fits Get file →
Q4_K_M1.5 GB 2.2 GB
Fits Get file →
Q4_K1.6 GB 2.2 GB
Fits Get file →
Q2_K2.7 GB 3.5 GB
Fits Get file →
IQ3_XS3.0 GB 3.9 GB
Fits Get file →
Q3_K_S3.2 GB 4.0 GB
Fits Get file →
IQ3_S3.2 GB 4.1 GB
Fits Get file →
IQ3_M3.3 GB 4.2 GB
Fits Get file →
Q3_K3.5 GB 4.4 GB
Fits Get file →
Q3_K_M3.5 GB 4.4 GB
Fits Get file →
Q5_K_S3.8 GB 4.8 GB
Fits Get file →
Q3_K_L3.8 GB 4.8 GB
Fits Get file →
IQ4_XS3.9 GB 4.9 GB
Fits Get file →
Q4_04.1 GB 5.1 GB
Fits Get file →
Q4_K_S4.1 GB 5.1 GB
Fits Get file →
IQ4_NL4.2 GB 5.2 GB
Fits Get file →
Q5_K4.3 GB 5.3 GB
Fits Get file →

What GPU do you need for Katayoon VPO SELM Zephyr 7B iter 2?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q3_K_S (3.2 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K (4.3 GB file, about 5.3 GB in use).

Which Katayoon VPO SELM Zephyr 7B iter 2 quant should you choose?

Q4_K_M is the usual starting point for Katayoon VPO SELM Zephyr 7B iter 2: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 0.1 GB, about 0.1 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 Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Trained context32,768 tokens

Source

Quantized byRichardErkhov
FamilyKatayoon
Downloads (HF)351
Last updated2024-08-03

Frequently asked questions about Katayoon VPO SELM Zephyr 7B iter 2

How much VRAM does Katayoon VPO SELM Zephyr 7B iter 2 need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.5 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 Katayoon VPO SELM Zephyr 7B iter 2 on an 8 GB GPU?

Yes, with Q5_K: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Katayoon VPO SELM Zephyr 7B iter 2 GGUF?

It depends on the quant: Q8_0 is 0.1 GB, Q6_K is 0.2 GB, Q5_1 is 0.2 GB, Q4_1 is 0.7 GB, Q5_K_M is 1.0 GB, Q5_0 is 1.4 GB and 16 more.

What context length does Katayoon VPO SELM Zephyr 7B iter 2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download Katayoon VPO SELM Zephyr 7B iter 2 GGUF?

The files are on Hugging Face in the RichardErkhov/Katayoon_-_VPO-SELM-Zephyr-7B-iter-2-gguf 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 RichardErkhov

All by RichardErkhov →

More Katayoon models

All Katayoon →

Other small models

All small models →