MI

osanseviero mistral instruct frankenmerge

MistralGGUF by RichardErkhovUpdated 2024-08-31
Download on Hugging Face
Parameters8.99B
Context32K
Layers40
Architecturellama
Smallest quant1.5 GB
Quick answer

osanseviero mistral instruct frankenmerge needs about 7.3 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 1.5 GB (IQ4_NL) to 9.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

osanseviero mistral instruct frankenmerge is a 8.99B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 1.5 GB (IQ4_NL) to 9.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL1.5 GB 3.4 GB
Fits Get file →
Q2_K3.4 GB 5.2 GB
Fits Get file →
IQ3_XS3.7 GB 5.6 GB
Fits Get file →
Q3_K_S3.9 GB 5.8 GB
Fits Get file →
IQ3_S3.9 GB 5.8 GB
Fits Get file →
IQ3_M4.1 GB 5.9 GB
Fits Get file →
Q3_K4.4 GB 6.2 GB
Fits Get file →
Q3_K_M4.4 GB 6.2 GB
Fits Get file →
Q3_K_L4.7 GB 6.6 GB
Fits Get file →
IQ4_XS4.9 GB 6.7 GB
Fits Get file →
Q4_05.1 GB 6.9 GB
Fits Get file →
Q4_K_S5.1 GB 7.0 GB
Fits Get file →
Q4_K5.4 GB 7.3 GB
Tight Get file →
Q4_K_M5.4 GB 7.3 GB
Tight Get file →
Q4_15.6 GB 7.5 GB
Tight Get file →
Q5_06.2 GB 8.0 GB
Too big Get file →
Q5_K_S6.2 GB 8.0 GB
Too big Get file →
Q5_K6.4 GB 8.2 GB
Too big Get file →
Q5_K_M6.4 GB 8.2 GB
Too big Get file →
Q5_16.8 GB 8.6 GB
Too big Get file →
Q6_K7.4 GB 9.2 GB
Too big Get file →
Q8_09.6 GB 11.4 GB
Too big Get file →

What GPU do you need for osanseviero mistral instruct frankenmerge?

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 IQ4_NL (1.5 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_0 (6.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).

Which osanseviero mistral instruct frankenmerge quant should you choose?

Q4_K_M is the usual starting point for osanseviero mistral instruct frankenmerge: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 9.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ4_NL at 1.5 GB, with the quality trade-offs that come with fewer bits. 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
Parameters8.99B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Licenseapache-2.0
Downloads (HF)283
Last updated2024-08-31

Frequently asked questions about osanseviero mistral instruct frankenmerge

How much VRAM does osanseviero mistral instruct frankenmerge need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.4 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 osanseviero mistral instruct frankenmerge on an 8 GB GPU?

Yes, with Q5_0: the 6.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of osanseviero mistral instruct frankenmerge GGUF?

It depends on the quant: IQ4_NL is 1.5 GB, Q2_K is 3.4 GB, IQ3_XS is 3.7 GB, Q3_K_S is 3.9 GB, IQ3_S is 3.9 GB, IQ3_M is 4.1 GB and 16 more.

What context length does osanseviero mistral instruct frankenmerge support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download osanseviero mistral instruct frankenmerge GGUF?

The files are on Hugging Face in the RichardErkhov/osanseviero_-_mistral-instruct-frankenmerge-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does osanseviero mistral instruct frankenmerge use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other small models

All small models →