SA

Samantha hermes3 8b model fixed Q6 K

SamanthaGGUF by Guilherme34Updated 2024-08-18
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant6.6 GB
Quick answer

Samantha hermes3 8b model fixed Q6 K needs about 8.2 GB of memory at Q6_K (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Samantha hermes3 8b model fixed Q6 K is a 8.03B-parameter Samantha model in GGUF format, quantized by Guilherme34. Its trained context length is 128K tokens. The repository has 1 quant file, from 6.6 GB (Q6_K) to 6.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K6.6 GB 8.2 GB
Too big Get file →

What GPU do you need for Samantha hermes3 8b model fixed Q6 K?

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 Q6_K (6.6 GB file, about 8.2 GB in use).

Which Samantha hermes3 8b model fixed Q6 K quant should you choose?

Q6_K (6.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byGuilherme34
FamilySamantha
Downloads (HF)8
Last updated2024-08-18

Frequently asked questions about Samantha hermes3 8b model fixed Q6 K

How much VRAM does Samantha hermes3 8b model fixed Q6 K need?

About 8.2 GB at Q6_K with an 8K context window. That is the 6.6 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 Samantha hermes3 8b model fixed Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Samantha hermes3 8b model fixed Q6 K GGUF?

It depends on the quant: Q6_K is 6.6 GB.

What context length does Samantha hermes3 8b model fixed Q6 K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Samantha hermes3 8b model fixed Q6 K GGUF?

The files are on Hugging Face in the Guilherme34/Samantha-hermes3-8b-model-fixed-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Samantha-hermes3-8b-model-fixed

Similar models

Browse all →

More from Guilherme34

All by Guilherme34 →

More Samantha models

All Samantha →

Other small models

All small models →