CO

CognitiveFusion2-4x7B-BF16

CognitivefusionGGUF by RichardErkhovUpdated 2024-06-15
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant8.8 GB
Quick answer

CognitiveFusion2-4x7B-BF16 needs about 12.0 GB of memory at BF16 (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 8.8 GB (BF16) to 11.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

CognitiveFusion2-4x7B-BF16 is a 24.2B-parameter Cognitivefusion model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 6 quant files, from 8.8 GB (BF16) to 11.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF168.8 GB 10.4 GB
Too big Get file →
BF169.9 GB 11.5 GB
Too big Get file →
BF1610.4 GB 12.0 GB
Too big Get file →
BF1610.5 GB 12.0 GB
Too big Get file →
BF1610.6 GB 12.2 GB
Too big Get file →
BF1611.6 GB 13.2 GB
Too big Get file →

What GPU do you need for CognitiveFusion2-4x7B-BF16?

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: the best quant that fits is BF16 (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (11.6 GB file, about 13.2 GB in use).

Which CognitiveFusion2-4x7B-BF16 quant should you choose?

BF16 (10.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is BF16 at 8.8 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byRichardErkhov
Downloads (HF)3
Last updated2024-06-15

Frequently asked questions about CognitiveFusion2-4x7B-BF16

How much VRAM does CognitiveFusion2-4x7B-BF16 need?

About 12.0 GB at BF16 with an 8K context window. That is the 10.4 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 CognitiveFusion2-4x7B-BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CognitiveFusion2-4x7B-BF16 GGUF?

It depends on the quant: BF16 is 8.8 GB, BF16 is 9.9 GB, BF16 is 10.4 GB, BF16 is 10.5 GB, BF16 is 10.6 GB, BF16 is 11.6 GB.

What context length does CognitiveFusion2-4x7B-BF16 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 CognitiveFusion2-4x7B-BF16 GGUF?

The files are on Hugging Face in the RichardErkhov/Kquant03_-_CognitiveFusion2-4x7B-BF16-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 Cognitivefusion models

All Cognitivefusion →

Other medium models

All medium models →