MI

SciPhi Mistral RAG Hermes 7B 32k

MistralGGUF by jtatmanUpdated 2024-02-25
Download on Hugging Face
Parameters6.59B
Context32K
Layers29
Architecturellama
Smallest quant2.5 GB
Quick answer

SciPhi Mistral RAG Hermes 7B 32k needs about 5.2 GB of memory at Q4_0 (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.5 GB (Q2_K) to 4.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.9 GB.

SciPhi Mistral RAG Hermes 7B 32k is a 6.59B-parameter Mistral model in GGUF format, quantized by jtatman. Its trained context length is 32K tokens. The repository has 3 quant files, from 2.5 GB (Q2_K) to 4.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 4.0 GB
Fits Get file →
Q4_03.7 GB 5.2 GB
Fits Get file →
—4.0 GB 5.4 GB
Fits Get file →

What GPU do you need for SciPhi Mistral RAG Hermes 7B 32k?

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: the best quant that fits is Q2_K (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (4.0 GB file, about 5.4 GB in use).

Which SciPhi Mistral RAG Hermes 7B 32k quant should you choose?

Q4_0 (3.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 2.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.59B
Layers29
Trained context32,768 tokens
KV cache (fp16)116 KB per token

Source

Quantized byjtatman
FamilyMistral
Downloads (HF)32
Last updated2024-02-25

Frequently asked questions about SciPhi Mistral RAG Hermes 7B 32k

How much VRAM does SciPhi Mistral RAG Hermes 7B 32k need?

About 5.2 GB at Q4_0 with an 8K context window. That is the 3.7 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 SciPhi Mistral RAG Hermes 7B 32k on an 8 GB GPU?

Yes, with the smaller files: the 4.0 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SciPhi Mistral RAG Hermes 7B 32k GGUF?

It depends on the quant: Q2_K is 2.5 GB, Q4_0 is 3.7 GB, file is 4.0 GB.

What context length does SciPhi Mistral RAG Hermes 7B 32k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.0 GB at 8K and 3.9 GB at 32K.

Where can I download SciPhi Mistral RAG Hermes 7B 32k GGUF?

The files are on Hugging Face in the jtatman/SciPhi-Mistral-RAG-Hermes-7B-32k-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 jtatman

All by jtatman →

More Mistral models

All Mistral →

Other small models

All small models →