LO

longchat 7b v1.5 32k Q8 0

LongchatGGUF by BroxyUpdated 2024-03-27
Download on Hugging Face
Parameters6.74B
Context32K
Layers32
Architecturellama
Smallest quant7.2 GB
Quick answer

longchat 7b v1.5 32k Q8 0 needs about 12.0 GB of memory at its main file (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

longchat 7b v1.5 32k Q8 0 is a 6.74B-parameter Longchat model in GGUF format, quantized by Broxy. Its trained context length is 32K tokens. The repository has 1 quant file, from 7.2 GB to 7.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.2 GB 12.0 GB
Too big Get file →

What GPU do you need for longchat 7b v1.5 32k Q8 0?

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 the main file (7.2 GB file, about 12.0 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byBroxy
FamilyLongchat
Downloads (HF)45
Last updated2024-03-27

Frequently asked questions about longchat 7b v1.5 32k Q8 0

How much VRAM does longchat 7b v1.5 32k Q8 0 need?

About 12.0 GB at its main file with an 8K context window. That is the 7.2 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 longchat 7b v1.5 32k Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of longchat 7b v1.5 32k Q8 0 GGUF?

It depends on the quant: file is 7.2 GB.

What context length does longchat 7b v1.5 32k Q8 0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download longchat 7b v1.5 32k Q8 0 GGUF?

The files are on Hugging Face in the Broxy/longchat-7b-v1.5-32k-Q8_0-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 Broxy

All by Broxy →

More Longchat models

All Longchat →

Other small models

All small models →