MA

matsuolab weblab 10b instruction sft

MatsuolabGGUF by mmngaUpdated 2023-09-02
Download on Hugging Face
Parameters10.7B
Context—
Layers—
Architecture—
Smallest quant6.0 GB
Quick answer

matsuolab weblab 10b instruction sft needs about 8.8 GB of memory at Q5_0 (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 6.0 GB (Q4_0) to 11.4 GB (Q8_0).

matsuolab weblab 10b instruction sft is a 10.7B-parameter Matsuolab model in GGUF format, quantized by mmnga. The repository has 3 quant files, from 6.0 GB (Q4_0) to 11.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_06.0 GB 7.3 GB
Tight Get file →
Q5_07.4 GB 8.8 GB
Too big Get file →
Q8_011.4 GB 13.3 GB
Too big Get file →

What GPU do you need for matsuolab weblab 10b instruction sft?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_0 (6.0 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_0 (7.4 GB file, about 8.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.3 GB in use).

Which matsuolab weblab 10b instruction sft quant should you choose?

Q5_0 (7.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 6.0 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

Parameters10.7B

Source

Quantized bymmnga
FamilyMatsuolab
Downloads (HF)163
Last updated2023-09-02

Frequently asked questions about matsuolab weblab 10b instruction sft

How much VRAM does matsuolab weblab 10b instruction sft need?

About 8.8 GB at Q5_0 with an 8K context window. That is the 7.4 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 matsuolab weblab 10b instruction sft on an 8 GB GPU?

Yes, with Q4_0: the 6.0 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of matsuolab weblab 10b instruction sft GGUF?

It depends on the quant: Q4_0 is 6.0 GB, Q5_0 is 7.4 GB, Q8_0 is 11.4 GB.

Where can I download matsuolab weblab 10b instruction sft GGUF?

The files are on Hugging Face in the mmnga/matsuolab-weblab-10b-instruction-sft-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 matsuolab weblab 10b instruction sft use?

Hugging Face lists the license as cc-by-nc-4.0. 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 mmnga

All by mmnga →

More Matsuolab models

All Matsuolab →

Other medium models

All medium models →