BE

BeyondInfinity 4x7B

BeyondinfinityGGUF by R136a1Updated 2024-04-16
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant13.7 GB
Quick answer

BeyondInfinity 4x7B needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 13.7 GB (Q4_K_S) to 14.6 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

BeyondInfinity 4x7B is a 24.2B-parameter Beyondinfinity model in GGUF format, quantized by R136a1. Its trained context length is 32K tokens. The repository has 2 quant files, from 13.7 GB (Q4_K_S) to 14.6 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →

What GPU do you need for BeyondInfinity 4x7B?

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 Q4_K_S (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (14.6 GB file, about 16.2 GB in use).

Which BeyondInfinity 4x7B quant should you choose?

Q4_K_M is the usual starting point for BeyondInfinity 4x7B: it balances file size and quality well. Here it is a 14.6 GB file.

If memory is tight, the smallest file is Q4_K_S at 13.7 GB, with the quality trade-offs that come with fewer bits. 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byR136a1
Downloads (HF)19
Last updated2024-04-16

Frequently asked questions about BeyondInfinity 4x7B

How much VRAM does BeyondInfinity 4x7B need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 BeyondInfinity 4x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BeyondInfinity 4x7B GGUF?

It depends on the quant: Q4_K_S is 13.7 GB, Q4_K_M is 14.6 GB.

What context length does BeyondInfinity 4x7B 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 BeyondInfinity 4x7B GGUF?

The files are on Hugging Face in the R136a1/BeyondInfinity-4x7B-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 R136a1

All by R136a1 →

More Beyondinfinity models

All Beyondinfinity →

Other medium models

All medium models →