MI

J.O.S.I.E.3 Beta3 slerp

MistralGGUF by Goekdeniz-GuelmezUpdated 2024-03-15
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.5 GB
Quick answer

J.O.S.I.E.3 Beta3 slerp needs about 5.7 GB of memory at Q4_K_S (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.5 GB (Q3_K_M) to 5.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

J.O.S.I.E.3 Beta3 slerp is a 7.24B-parameter Mistral model in GGUF format, quantized by Goekdeniz-Guelmez. Its trained context length is 32K tokens. The repository has 3 quant files, from 3.5 GB (Q3_K_M) to 5.1 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →

What GPU do you need for J.O.S.I.E.3 Beta3 slerp?

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: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).

Which J.O.S.I.E.3 Beta3 slerp quant should you choose?

Q4_K_S (4.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_M at 3.5 GB, with the quality trade-offs that come with fewer bits. 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byGoekdeniz-Guelmez
FamilyMistral
Downloads (HF)156
Last updated2024-03-15

Frequently asked questions about J.O.S.I.E.3 Beta3 slerp

How much VRAM does J.O.S.I.E.3 Beta3 slerp need?

About 5.7 GB at Q4_K_S with an 8K context window. That is the 4.1 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 J.O.S.I.E.3 Beta3 slerp on an 8 GB GPU?

Yes, with Q5_K_M: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of J.O.S.I.E.3 Beta3 slerp GGUF?

It depends on the quant: Q3_K_M is 3.5 GB, Q4_K_S is 4.1 GB, Q5_K_M is 5.1 GB.

What context length does J.O.S.I.E.3 Beta3 slerp support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download J.O.S.I.E.3 Beta3 slerp GGUF?

The files are on Hugging Face in the Goekdeniz-Guelmez/J.O.S.I.E.3-Beta3-slerp-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 Hercules-3.1-Mistral-7B

Similar models

Browse all →

More from Goekdeniz-Guelmez

All by Goekdeniz-Guelmez →

More Mistral models

All Mistral →

Other small models

All small models →