CH

Chameleon 7b Hf

ChameleonGGUF by nopperlUpdated 2024-09-26
Download on Hugging Face
Parameters7.01B
Context4K
Layers32
Architecturechameleon
Smallest quant4.3 GB
Quick answer

Chameleon 7b Hf needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 4.3 GB (Q4_K_M) to 14.0 GB (F16).

Chameleon 7b Hf is a 7.01B-parameter Chameleon model in GGUF format, quantized by nopperl. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.3 GB (Q4_K_M) to 14.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.3 GB 6.9 GB
Fits Get file →
F1614.0 GB 16.7 GB
Too big Get file →

What GPU do you need for Chameleon 7b Hf?

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 Q4_K_M (4.3 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.3 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.0 GB file, about 18.8 GB in use).

Which Chameleon 7b Hf quant should you choose?

Q4_K_M is the usual starting point for Chameleon 7b Hf: it balances file size and quality well. Here it is a 4.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechameleon
Parameters7.01B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bynopperl
FamilyChameleon
Downloads (HF)122
Last updated2024-09-26

Frequently asked questions about Chameleon 7b Hf

How much VRAM does Chameleon 7b Hf need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 Chameleon 7b Hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Chameleon 7b Hf GGUF?

It depends on the quant: Q4_K_M is 4.3 GB, F16 is 14.0 GB.

What context length does Chameleon 7b Hf support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Chameleon 7b Hf GGUF?

The files are on Hugging Face in the nopperl/chameleon-7b-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 nopperl

All by nopperl →

More Chameleon models

All Chameleon →

Other small models

All small models →