PH

phoenix inst chat 7b v1.1

PhoenixGGUF by SosnitskijUpdated 2024-01-30
Download on Hugging Face
Parameters8.1B
Context4K
Layers30
Architecturebloom
Smallest quant6.0 GB
Quick answer

phoenix inst chat 7b v1.1 needs about 10.6 GB of memory at Q5_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

phoenix inst chat 7b v1.1 is a 8.1B-parameter Phoenix model in GGUF format, quantized by Sosnitskij. Its trained context length is 4K tokens. The repository has 1 quant file, from 6.0 GB (Q5_K_M) to 6.0 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M6.0 GB 8.6 GB
Too big Get file →

What GPU do you need for phoenix inst chat 7b v1.1?

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: the best quant that fits is Q5_K_M (6.0 GB file, about 10.6 GB in use).

Which phoenix inst chat 7b v1.1 quant should you choose?

Q5_K_M (6.0 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

Architecturebloom
Parameters8.1B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized bySosnitskij
FamilyPhoenix
Licenseapache-2.0
Downloads (HF)13
Last updated2024-01-30

Frequently asked questions about phoenix inst chat 7b v1.1

How much VRAM does phoenix inst chat 7b v1.1 need?

About 10.6 GB at Q5_K_M with an 8K context window. That is the 6.0 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 phoenix inst chat 7b v1.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phoenix inst chat 7b v1.1 GGUF?

It depends on the quant: Q5_K_M is 6.0 GB.

What context length does phoenix inst chat 7b v1.1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download phoenix inst chat 7b v1.1 GGUF?

The files are on Hugging Face in the Sosnitskij/phoenix-inst-chat-7b-v1.1-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 phoenix inst chat 7b v1.1 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 Sosnitskij

All by Sosnitskij →

More Phoenix models

All Phoenix →

Other small models

All small models →