GP

gpt-sw3-6.7b-v2

GptGGUF by timpal0lUpdated 2026-04-20
Download on Hugging Face
Parameters6.98B
Context2K
Layers32
Architecturegpt2
Smallest quant4.5 GB
Quick answer

gpt-sw3-6.7b-v2 needs about 9.3 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 4.5 GB (Q4_K_M) to 5.2 GB (Q5_K_M).

gpt-sw3-6.7b-v2 is a 6.98B-parameter Gpt model in GGUF format, quantized by timpal0l. Its trained context length is 2K tokens. The repository has 2 quant files, from 4.5 GB (Q4_K_M) to 5.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.5 GB 6.1 GB
Fits Get file →
Q5_K_M5.2 GB 6.8 GB
Fits Get file →

What GPU do you need for gpt-sw3-6.7b-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: 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 (5.2 GB file, about 10.0 GB in use).

Which gpt-sw3-6.7b-v2 quant should you choose?

Q4_K_M is the usual starting point for gpt-sw3-6.7b-v2: it balances file size and quality well. Here it is a 4.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters6.98B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bytimpal0l
FamilyGpt
Downloads (HF)14
Last updated2026-04-20

Frequently asked questions about gpt-sw3-6.7b-v2

How much VRAM does gpt-sw3-6.7b-v2 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 4.5 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 gpt-sw3-6.7b-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gpt-sw3-6.7b-v2 GGUF?

It depends on the quant: Q4_K_M is 4.5 GB, Q5_K_M is 5.2 GB.

What context length does gpt-sw3-6.7b-v2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download gpt-sw3-6.7b-v2 GGUF?

The files are on Hugging Face in the timpal0l/gpt-sw3-6.7b-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 timpal0l

All by timpal0l →

More Gpt models

All Gpt →

Other small models

All small models →