MI

cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser

MistralGGUF by werweweqrUpdated 2024-07-08
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.0 GB
Quick answer

cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser needs about 6.6 GB of memory at Q5_0 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser is a 7.24B-parameter Mistral model in GGUF format, quantized by werweweqr. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.0 GB (Q5_0) to 5.0 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_05.0 GB 6.6 GB
Fits Get file →

What GPU do you need for cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser?

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: the best quant that fits is Q5_0 (5.0 GB file, about 6.6 GB in use).

Which cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser quant should you choose?

Q5_0 (5.0 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.

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 bywerweweqr
FamilyMistral
Licensemit
Downloads (HF)8
Last updated2024-07-08

Frequently asked questions about cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser

How much VRAM does cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser need?

About 6.6 GB at Q5_0 with an 8K context window. That is the 5.0 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 cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser on an 8 GB GPU?

Yes, with Q5_0: the 5.0 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser GGUF?

It depends on the quant: Q5_0 is 5.0 GB.

What context length does cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser 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 cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser GGUF?

The files are on Hugging Face in the werweweqr/mistral repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does cognitivecomputations_dolphin-2.6-mistral-7b-dpo-laser use?

Hugging Face lists the license as mit. 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 Mistral models

All Mistral →

Other small models

All small models →