MO

Monsoon 7B exp 1

MonsoonGGUF by yuuko-ethUpdated 2024-02-04
Download on Hugging Face
Parameters7.49B
Context32K
Layers32
Architecturellama
Smallest quant4.3 GB
Quick answer

Monsoon 7B exp 1 needs about 6.8 GB of memory at Q5_0 (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 4.3 GB (Q4_0) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Monsoon 7B exp 1 is a 7.49B-parameter Monsoon model in GGUF format, quantized by yuuko-eth. Its trained context length is 32K tokens. The repository has 4 quant files, from 4.3 GB (Q4_0) to 8.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.3 GB 5.9 GB
Fits Get file →
Q5_05.2 GB 6.8 GB
Fits Get file →
Q6_K6.1 GB 7.7 GB
Tight Get file →
Q8_08.0 GB 9.5 GB
Too big Get file →

What GPU do you need for Monsoon 7B exp 1?

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: the best quant that fits is Q4_0 (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.5 GB in use).

Which Monsoon 7B exp 1 quant should you choose?

Q5_0 (5.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 4.3 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
Parameters7.49B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byyuuko-eth
FamilyMonsoon
Licenseunknown
Downloads (HF)99
Last updated2024-02-04

Frequently asked questions about Monsoon 7B exp 1

How much VRAM does Monsoon 7B exp 1 need?

About 6.8 GB at Q5_0 with an 8K context window. That is the 5.2 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 Monsoon 7B exp 1 on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Monsoon 7B exp 1 GGUF?

It depends on the quant: Q4_0 is 4.3 GB, Q5_0 is 5.2 GB, Q6_K is 6.1 GB, Q8_0 is 8.0 GB.

What context length does Monsoon 7B exp 1 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 Monsoon 7B exp 1 GGUF?

The files are on Hugging Face in the yuuko-eth/Monsoon-7B-exp-1-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 Monsoon 7B exp 1 use?

Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from yuuko-eth

All by yuuko-eth →

More Monsoon models

All Monsoon →

Other small models

All small models →