EV

EvoLLM JP A v1 7B IQ4 XS

EvollmGGUF by sehiroUpdated 2024-09-15
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.9 GB
Quick answer

EvoLLM JP A v1 7B IQ4 XS needs about 5.5 GB of memory at IQ4_XS (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

EvoLLM JP A v1 7B IQ4 XS is a 7.24B-parameter Evollm model in GGUF format, quantized by sehiro. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.9 GB (IQ4_XS) to 3.9 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS3.9 GB 5.5 GB
Fits Get file →

What GPU do you need for EvoLLM JP A v1 7B IQ4 XS?

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 IQ4_XS (3.9 GB file, about 5.5 GB in use).

Which EvoLLM JP A v1 7B IQ4 XS quant should you choose?

IQ4_XS (3.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 bysehiro
FamilyEvollm
Licenseapache-2.0
Downloads (HF)18
Last updated2024-09-15

Frequently asked questions about EvoLLM JP A v1 7B IQ4 XS

How much VRAM does EvoLLM JP A v1 7B IQ4 XS need?

About 5.5 GB at IQ4_XS with an 8K context window. That is the 3.9 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 EvoLLM JP A v1 7B IQ4 XS on an 8 GB GPU?

Yes, with IQ4_XS: the 3.9 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EvoLLM JP A v1 7B IQ4 XS GGUF?

It depends on the quant: IQ4_XS is 3.9 GB.

What context length does EvoLLM JP A v1 7B IQ4 XS 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 EvoLLM JP A v1 7B IQ4 XS GGUF?

The files are on Hugging Face in the sehiro/EvoLLM-JP-A-v1-7B-IQ4_XS-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 EvoLLM JP A v1 7B IQ4 XS 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 EvoLLM-JP-A-v1-7B

Similar models

Browse all →

More from sehiro

All by sehiro →

More Evollm models

All Evollm →

Other small models

All small models →