EV

Everyone-Coder-4x7b-Base

EveryoneGGUF by victorburUpdated 2024-07-04
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant11.6 GB
Quick answer

Everyone-Coder-4x7b-Base needs about 13.2 GB of memory at Q3_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Everyone-Coder-4x7b-Base is a 24.2B-parameter Everyone model in GGUF format, quantized by victorbur. Its trained context length is 32K tokens. The repository has 1 quant file, from 11.6 GB (Q3_K_M) to 11.6 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M11.6 GB 13.2 GB
Too big Get file →

What GPU do you need for Everyone-Coder-4x7b-Base?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (11.6 GB file, about 13.2 GB in use).

Which Everyone-Coder-4x7b-Base quant should you choose?

Q3_K_M (11.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byvictorbur
FamilyEveryone
Licensecc-by-4.0
Downloads (HF)7
Last updated2024-07-04

Frequently asked questions about Everyone-Coder-4x7b-Base

How much VRAM does Everyone-Coder-4x7b-Base need?

About 13.2 GB at Q3_K_M with an 8K context window. That is the 11.6 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 Everyone-Coder-4x7b-Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Everyone-Coder-4x7b-Base GGUF?

It depends on the quant: Q3_K_M is 11.6 GB.

What context length does Everyone-Coder-4x7b-Base 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 Everyone-Coder-4x7b-Base GGUF?

The files are on Hugging Face in the victorbur/Everyone-Coder-4x7b-Base-Q3_K_M-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 Everyone-Coder-4x7b-Base use?

Hugging Face lists the license as cc-by-4.0. 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 Everyone-Coder-4x7b-Base

Similar models

Browse all →

More from victorbur

All by victorbur →

More Everyone models

All Everyone →

Other medium models

All medium models →