QU

quantized q6 k

QuantizedGGUF by YoungDeukUpdated 2024-12-10
Download on Hugging Face
Parameters7.82B
Context4K
Layers32
Architectureexaone
Smallest quant6.4 GB
Quick answer

quantized q6 k needs about 8.0 GB of memory at Q6_K (a 6.4 GB file) with an 8K context window, so it fits on a 8 GB GPU.

quantized q6 k is a 7.82B-parameter Quantized model in GGUF format, quantized by YoungDeuk. Its trained context length is 4K tokens. The repository has 1 quant file, from 6.4 GB (Q6_K) to 6.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K6.4 GB 7.5 GB
Tight Get file →

What GPU do you need for quantized q6 k?

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: the best quant that fits is Q6_K (6.4 GB file, about 8.0 GB in use).

Which quantized q6 k quant should you choose?

Q6_K (6.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureexaone
Parameters7.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byYoungDeuk
FamilyQuantized
Downloads (HF)8
Last updated2024-12-10

Frequently asked questions about quantized q6 k

How much VRAM does quantized q6 k need?

About 8.0 GB at Q6_K with an 8K context window. That is the 6.4 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 quantized q6 k on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quantized q6 k GGUF?

It depends on the quant: Q6_K is 6.4 GB.

What context length does quantized q6 k support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download quantized q6 k GGUF?

The files are on Hugging Face in the YoungDeuk/quantized_q6_k 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 YoungDeuk

All by YoungDeuk →

More Quantized models

All Quantized →

Other small models

All small models →