GE

GEITje 7B chat v2

GeitjeGGUF by cherryboiUpdated 2024-04-05
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

GEITje 7B chat v2 needs about 5.7 GB of memory at Q4_0 (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.7 GB (Q2_K) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

GEITje 7B chat v2 is a 7.24B-parameter Geitje model in GGUF format, quantized by cherryboi. Its trained context length is 32K tokens. The repository has 5 quant files, from 2.7 GB (Q2_K) to 5.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →

What GPU do you need for GEITje 7B chat v2?

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_0 (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).

Which GEITje 7B chat v2 quant should you choose?

Q4_0 (4.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 bycherryboi
FamilyGeitje
Downloads (HF)17
Last updated2024-04-05

Frequently asked questions about GEITje 7B chat v2

How much VRAM does GEITje 7B chat v2 need?

About 5.7 GB at Q4_0 with an 8K context window. That is the 4.1 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 GEITje 7B chat v2 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GEITje 7B chat v2 GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_M is 3.5 GB, Q4_0 is 4.1 GB, Q5_K_S is 5.0 GB, Q6_K is 5.9 GB.

What context length does GEITje 7B chat v2 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 GEITje 7B chat v2 GGUF?

The files are on Hugging Face in the cherryboi/GEITje-7B-chat-v2-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 cherryboi

All by cherryboi →

More Geitje models

All Geitje →

Other small models

All small models →