MI

phi2_mistral-silver

MistralGGUF by bakkensusUpdated 2024-04-25
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.1 GB
Quick answer

phi2_mistral-silver needs about 6.7 GB of memory at its main file (a 5.1 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.

phi2_mistral-silver is a 7.24B-parameter Mistral model in GGUF format, quantized by bakkensus. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.1 GB to 5.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.1 GB 6.7 GB
Fits Get file →

What GPU do you need for phi2_mistral-silver?

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 the main file (5.1 GB file, about 6.7 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybakkensus
FamilyMistral
Downloads (HF)4
Last updated2024-04-25

Frequently asked questions about phi2_mistral-silver

How much VRAM does phi2_mistral-silver need?

About 6.7 GB at its main file with an 8K context window. That is the 5.1 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 phi2_mistral-silver on an 8 GB GPU?

Yes, with the smaller files: 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 phi2_mistral-silver GGUF?

It depends on the quant: file is 5.1 GB.

What context length does phi2_mistral-silver 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 phi2_mistral-silver GGUF?

The files are on Hugging Face in the bakkensus/mistral-silver-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 bakkensus

All by bakkensus →

More Mistral models

All Mistral →

Other small models

All small models →