MU

multimaster-7b-v6

MultimasterGGUF by hus960Updated 2024-04-28
Download on Hugging Face
Parameters35.4B
Context32K
Layers32
Architecturellama
Smallest quant21.4 GB
Quick answer

multimaster-7b-v6 needs about 23.0 GB of memory at Q4_K_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

multimaster-7b-v6 is a 35.4B-parameter Multimaster model in GGUF format, quantized by hus960. Its trained context length is 32K tokens. The repository has 1 quant file, from 21.4 GB (Q4_K_M) to 21.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.4 GB 23.0 GB
Too big Get file →

What GPU do you need for multimaster-7b-v6?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.4 GB file, about 23.0 GB in use).

Which multimaster-7b-v6 quant should you choose?

Q4_K_M is the usual starting point for multimaster-7b-v6: it balances file size and quality well. Here it is a 21.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters35.4B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byhus960
Licenseapache-2.0
Downloads (HF)16
Last updated2024-04-28

Frequently asked questions about multimaster-7b-v6

How much VRAM does multimaster-7b-v6 need?

About 23.0 GB at Q4_K_M with an 8K context window. That is the 21.4 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 multimaster-7b-v6 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of multimaster-7b-v6 GGUF?

It depends on the quant: Q4_K_M is 21.4 GB.

What context length does multimaster-7b-v6 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 multimaster-7b-v6 GGUF?

The files are on Hugging Face in the hus960/multimaster-7b-v6-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 multimaster-7b-v6 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.

Similar models

Browse all →

More from hus960

All by hus960 →

More Multimaster models

All Multimaster →

Other large models

All large models →