FU

LogoS-7Bx2-MoE-13B-v0.2

FusionnetGGUF by rinaldowUpdated 2024-04-10
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant7.8 GB
Quick answer

LogoS-7Bx2-MoE-13B-v0.2 needs about 9.4 GB of memory at Q4_K_M (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

LogoS-7Bx2-MoE-13B-v0.2 is a 12.9B-parameter Fusionnet model in GGUF format, quantized by rinaldow. Its trained context length is 32K tokens. The repository has 1 quant file, from 7.8 GB (Q4_K_M) to 7.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.8 GB 9.4 GB
Too big Get file →

What GPU do you need for LogoS-7Bx2-MoE-13B-v0.2?

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 Q4_K_M (7.8 GB file, about 9.4 GB in use).

Which LogoS-7Bx2-MoE-13B-v0.2 quant should you choose?

Q4_K_M is the usual starting point for LogoS-7Bx2-MoE-13B-v0.2: it balances file size and quality well. Here it is a 7.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byrinaldow
FamilyFusionnet
Licenseapache-2.0
Downloads (HF)12
Last updated2024-04-10

Frequently asked questions about LogoS-7Bx2-MoE-13B-v0.2

How much VRAM does LogoS-7Bx2-MoE-13B-v0.2 need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 7.8 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 LogoS-7Bx2-MoE-13B-v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LogoS-7Bx2-MoE-13B-v0.2 GGUF?

It depends on the quant: Q4_K_M is 7.8 GB.

What context length does LogoS-7Bx2-MoE-13B-v0.2 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 LogoS-7Bx2-MoE-13B-v0.2 GGUF?

The files are on Hugging Face in the rinaldow/LogoS-7Bx2-MoE-13B-v0.2-Q4_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 LogoS-7Bx2-MoE-13B-v0.2 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 FusionNet_7Bx2_MoE_14B

Similar models

Browse all →

More from rinaldow

All by rinaldow →

More Fusionnet models

All Fusionnet →

Other medium models

All medium models →