TW

Twilight SCE 12B

TwilightGGUF by yamatazenUpdated 2025-04-20
Download on Hugging Face
Parameters12.2B
Context128K
Layers40
Architecturellama
Smallest quant7.5 GB
Quick answer

Twilight SCE 12B needs about 9.3 GB of memory at Q4_K_M (a 7.5 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.

Twilight SCE 12B is a 12.2B-parameter Twilight model in GGUF format, quantized by yamatazen. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.5 GB (Q4_K_M) to 7.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.5 GB 9.3 GB
Too big Get file →

What GPU do you need for Twilight SCE 12B?

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 Q4_K_M (7.5 GB file, about 9.3 GB in use).

Which Twilight SCE 12B quant should you choose?

Q4_K_M is the usual starting point for Twilight SCE 12B: it balances file size and quality well. Here it is a 7.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byyamatazen
FamilyTwilight
Downloads (HF)23
Last updated2025-04-20

Frequently asked questions about Twilight SCE 12B

How much VRAM does Twilight SCE 12B need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Twilight SCE 12B 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 Twilight SCE 12B GGUF?

It depends on the quant: Q4_K_M is 7.5 GB.

What context length does Twilight SCE 12B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Twilight SCE 12B GGUF?

The files are on Hugging Face in the yamatazen/Twilight-SCE-12B-Q4_K_M-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 Twilight-SCE-12B

Similar models

Browse all →

More from yamatazen

All by yamatazen →

More Twilight models

All Twilight →

Other medium models

All medium models →