OR

Original Metallama 6Epoch Graphofloss 2

OriginalGGUF by prabal123Updated 2024-08-20
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant3.3 GB
Quick answer

Original Metallama 6Epoch Graphofloss 2 needs about 8.1 GB of memory at Q3_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 3.3 GB (Q3_K_M) to 4.2 GB (Q4_1).

Original Metallama 6Epoch Graphofloss 2 is a 6.74B-parameter Original model in GGUF format, quantized by prabal123. Its trained context length is 4K tokens. The repository has 2 quant files, from 3.3 GB (Q3_K_M) to 4.2 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q4_14.2 GB 6.9 GB
Fits Get file →

What GPU do you need for Original Metallama 6Epoch Graphofloss 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_1 (4.2 GB file, about 9.0 GB in use).

Which Original Metallama 6Epoch Graphofloss 2 quant should you choose?

Q3_K_M (3.3 GB) is the middle option in this repository. 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byprabal123
FamilyOriginal
Downloads (HF)5
Last updated2024-08-20

Frequently asked questions about Original Metallama 6Epoch Graphofloss 2

How much VRAM does Original Metallama 6Epoch Graphofloss 2 need?

About 8.1 GB at Q3_K_M with an 8K context window. That is the 3.3 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 Original Metallama 6Epoch Graphofloss 2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Original Metallama 6Epoch Graphofloss 2 GGUF?

It depends on the quant: Q3_K_M is 3.3 GB, Q4_1 is 4.2 GB.

What context length does Original Metallama 6Epoch Graphofloss 2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Original Metallama 6Epoch Graphofloss 2 GGUF?

The files are on Hugging Face in the prabal123/Original-Metallama-6Epoch-Graphofloss-2-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 prabal123

All by prabal123 →

More Original models

All Original →

Other small models

All small models →