NO

NousHermesSolar10.7B q4 0

NoushermessolarGGUF by cajukevUpdated 2024-03-25
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant6.1 GB
Quick answer

NousHermesSolar10.7B q4 0 needs about 8.2 GB of memory at Q4_0 (a 6.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

NousHermesSolar10.7B q4 0 is a 10.7B-parameter Noushermessolar model in GGUF format, quantized by cajukev. Its trained context length is 4K tokens. The repository has 1 quant file, from 6.1 GB (Q4_0) to 6.1 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_06.1 GB 7.4 GB
Tight Get file →

What GPU do you need for NousHermesSolar10.7B q4 0?

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_0 (6.1 GB file, about 8.2 GB in use).

Which NousHermesSolar10.7B q4 0 quant should you choose?

Q4_0 (6.1 GB) is the middle option in this repository. 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
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bycajukev
Downloads (HF)5
Last updated2024-03-25

Frequently asked questions about NousHermesSolar10.7B q4 0

How much VRAM does NousHermesSolar10.7B q4 0 need?

About 8.2 GB at Q4_0 with an 8K context window. That is the 6.1 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 NousHermesSolar10.7B q4 0 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 NousHermesSolar10.7B q4 0 GGUF?

It depends on the quant: Q4_0 is 6.1 GB.

What context length does NousHermesSolar10.7B q4 0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download NousHermesSolar10.7B q4 0 GGUF?

The files are on Hugging Face in the cajukev/NousHermesSolar10.7B_q4_0 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 →

Other medium models

All medium models →