GH

ghost-7b-alpha

GhostGGUF by RichardErkhovUpdated 2024-05-19
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

ghost-7b-alpha needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 2.7 GB (Q2_K) to 4.6 GB (Q4_1). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

ghost-7b-alpha is a 7.24B-parameter Ghost model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 15 quant files, from 2.7 GB (Q2_K) to 4.6 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K3.5 GB 5.1 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
IQ4_NL4.2 GB 5.7 GB
Fits Get file →
Q4_K4.4 GB 5.9 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q4_14.6 GB 6.1 GB
Fits Get file →

What GPU do you need for ghost-7b-alpha?

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: the best quant that fits is Q4_K (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_1 (4.6 GB file, about 6.1 GB in use).

Which ghost-7b-alpha quant should you choose?

Q4_K_M is the usual starting point for ghost-7b-alpha: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is Q2_K at 2.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byRichardErkhov
FamilyGhost
Downloads (HF)70
Last updated2024-05-19

Frequently asked questions about ghost-7b-alpha

How much VRAM does ghost-7b-alpha need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 ghost-7b-alpha on an 8 GB GPU?

Yes, with Q4_1: the 4.6 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ghost-7b-alpha GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K is 3.5 GB and 9 more.

What context length does ghost-7b-alpha 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 ghost-7b-alpha GGUF?

The files are on Hugging Face in the RichardErkhov/ghost-x_-_ghost-7b-alpha-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 RichardErkhov

All by RichardErkhov →

More Ghost models

All Ghost →

Other small models

All small models →