FU

FusionNet 7Bx2 MoE 14B

FusionnetGGUF by Nan-DoUpdated 2024-01-21
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant5.6 GB
Quick answer

FusionNet 7Bx2 MoE 14B needs about 9.7 GB of memory at Q4_1 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.6 GB (Q3_K_S) to 25.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

FusionNet 7Bx2 MoE 14B is a 12.9B-parameter Fusionnet model in GGUF format, quantized by Nan-Do. Its trained context length is 32K tokens. The repository has 11 quant files, from 5.6 GB (Q3_K_S) to 25.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S5.6 GB 7.2 GB
Fits Get file →
Q3_K6.2 GB 7.8 GB
Tight Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_K_S7.3 GB 8.9 GB
Too big Get file →
Q4_K7.8 GB 9.4 GB
Too big Get file →
Q4_18.1 GB 9.7 GB
Too big Get file →
Q5_K_S8.9 GB 10.4 GB
Too big Get file →
Q5_K9.1 GB 10.7 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →
Q8_013.7 GB 15.3 GB
Too big Get file →
F1625.8 GB 27.3 GB
Too big Get file →

What GPU do you need for FusionNet 7Bx2 MoE 14B?

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: the best quant that fits is Q3_K (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (25.8 GB file, about 27.3 GB in use).

Which FusionNet 7Bx2 MoE 14B quant should you choose?

Q4_1 (8.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_S at 5.6 GB, with the quality trade-offs that come with fewer bits. 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
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byNan-Do
FamilyFusionnet
Licensemit
Downloads (HF)143
Last updated2024-01-21

Frequently asked questions about FusionNet 7Bx2 MoE 14B

How much VRAM does FusionNet 7Bx2 MoE 14B need?

About 9.7 GB at Q4_1 with an 8K context window. That is the 8.1 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 FusionNet 7Bx2 MoE 14B on an 8 GB GPU?

Yes, with Q3_K: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FusionNet 7Bx2 MoE 14B GGUF?

It depends on the quant: Q3_K_S is 5.6 GB, Q3_K is 6.2 GB, Q4_0 is 7.3 GB, Q4_K_S is 7.3 GB, Q4_K is 7.8 GB, Q4_1 is 8.1 GB and 5 more.

What context length does FusionNet 7Bx2 MoE 14B 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 FusionNet 7Bx2 MoE 14B GGUF?

The files are on Hugging Face in the Nan-Do/FusionNet_7Bx2_MoE_14B-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 FusionNet 7Bx2 MoE 14B use?

Hugging Face lists the license as mit. 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 Nan-Do

All by Nan-Do →

More Fusionnet models

All Fusionnet →

Other medium models

All medium models →