MI

Mira 70B v0.8

MiraGGUF by gotzmannUpdated 2024-04-19
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant41.4 GB
Quick answer

Mira 70B v0.8 needs about 44.6 GB of memory at its main file (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU.

Mira 70B v0.8 is a 69B-parameter Mira model in GGUF format, quantized by gotzmann. Its trained context length is 4K tokens. The repository has 1 quant file, from 41.4 GB to 41.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—41.4 GB 43.3 GB
Too big Get file →

What GPU do you need for Mira 70B v0.8?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is the main file (41.4 GB file, about 44.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bygotzmann
FamilyMira
Downloads (HF)4
Last updated2024-04-19

Frequently asked questions about Mira 70B v0.8

How much VRAM does Mira 70B v0.8 need?

About 44.6 GB at its main file with an 8K context window. That is the 41.4 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 Mira 70B v0.8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mira 70B v0.8 GGUF?

It depends on the quant: file is 41.4 GB.

What context length does Mira 70B v0.8 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Mira 70B v0.8 GGUF?

The files are on Hugging Face in the gotzmann/Mira-70B-v0.8-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 gotzmann

All by gotzmann →

More Mira models

All Mira →

Other large models

All large models →