LY

NM 12B Lyris dev 3 Q6 K

LyrisGGUF by v000000Updated 2024-09-05
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant10.1 GB
Quick answer

NM 12B Lyris dev 3 Q6 K needs about 11.9 GB of memory at Q6_K (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

NM 12B Lyris dev 3 Q6 K is a 12.2B-parameter Lyris model in GGUF format, quantized by v000000. Its trained context length is 1000K tokens. The repository has 1 quant file, from 10.1 GB (Q6_K) to 10.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K10.1 GB 11.9 GB
Too big Get file →

What GPU do you need for NM 12B Lyris dev 3 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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).

Which NM 12B Lyris dev 3 Q6 K quant should you choose?

Q6_K (10.1 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

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byv000000
FamilyLyris
Downloads (HF)11
Last updated2024-09-05

Frequently asked questions about NM 12B Lyris dev 3 Q6 K

How much VRAM does NM 12B Lyris dev 3 Q6 K need?

About 11.9 GB at Q6_K with an 8K context window. That is the 10.1 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 NM 12B Lyris dev 3 Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NM 12B Lyris dev 3 Q6 K GGUF?

It depends on the quant: Q6_K is 10.1 GB.

What context length does NM 12B Lyris dev 3 Q6 K support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download NM 12B Lyris dev 3 Q6 K GGUF?

The files are on Hugging Face in the v000000/NM-12B-Lyris-dev-3-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of NM-12B-Lyris-dev-3

Similar models

Browse all →

More from v000000

All by v000000 →

More Lyris models

All Lyris →

Other medium models

All medium models →