MI

ehartford dolphin 2.5 mixtral 8x7b

MistralGGUF by PsiPiUpdated 2024-01-31
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant20.3 GB
Quick answer

ehartford dolphin 2.5 mixtral 8x7b needs about 21.9 GB of memory at Q3_K_L (a 20.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

ehartford dolphin 2.5 mixtral 8x7b is a 46.7B-parameter Mistral model in GGUF format, quantized by PsiPi. Its trained context length is 32K tokens. The repository has 1 quant file, from 20.3 GB (Q3_K_L) to 20.3 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L20.3 GB 21.9 GB
Too big Get file →

What GPU do you need for ehartford dolphin 2.5 mixtral 8x7b?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q3_K_L (20.3 GB file, about 21.9 GB in use).

Which ehartford dolphin 2.5 mixtral 8x7b quant should you choose?

Q3_K_L (20.3 GB) is the middle option in this repository. 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
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byPsiPi
FamilyMistral
Downloads (HF)131
Last updated2024-01-31

Frequently asked questions about ehartford dolphin 2.5 mixtral 8x7b

How much VRAM does ehartford dolphin 2.5 mixtral 8x7b need?

About 21.9 GB at Q3_K_L with an 8K context window. That is the 20.3 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 ehartford dolphin 2.5 mixtral 8x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ehartford dolphin 2.5 mixtral 8x7b GGUF?

It depends on the quant: Q3_K_L is 20.3 GB.

What context length does ehartford dolphin 2.5 mixtral 8x7b 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 ehartford dolphin 2.5 mixtral 8x7b GGUF?

The files are on Hugging Face in the PsiPi/ehartford_dolphin-2.5-mixtral-8x7b-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 PsiPi

All by PsiPi →

More Mistral models

All Mistral →

Other large models

All large models →