TH

The_Darkside 16.6B

TheGGUF by mradermacherUpdated 2025-12-07
Download on Hugging Face
Parameters16.6B
Context1000K
Layers56
Architecturellama
Smallest quant0.0 GB
Quick answer

The_Darkside 16.6B needs about 12.5 GB of memory at Q4_K_M (a 10.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 13.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

The_Darkside 16.6B is a 16.6B-parameter The model in GGUF format, quantized by mradermacher. Its trained context length is 1000K tokens. The repository has 25 quant files, from 0.0 GB to 13.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.4 GB
Fits Get file →
IQ1_S3.9 GB 6.3 GB
Fits Get file →
IQ1_M4.2 GB 6.6 GB
Fits Get file →
IQ2_XXS4.8 GB 7.1 GB
Fits Get file →
IQ2_XS5.2 GB 7.6 GB
Tight Get file →
IQ2_S5.5 GB 7.9 GB
Tight Get file →
IQ2_M5.9 GB 8.3 GB
Too big Get file →
Q2_K_S6.0 GB 8.4 GB
Too big Get file →
Q2_K6.4 GB 8.8 GB
Too big Get file →
IQ3_XXS6.6 GB 9.0 GB
Too big Get file →
IQ3_XS7.1 GB 9.5 GB
Too big Get file →
Q3_K_S7.4 GB 9.8 GB
Too big Get file →
IQ3_S7.4 GB 9.8 GB
Too big Get file →
IQ3_M7.7 GB 10.1 GB
Too big Get file →
Q3_K_M8.2 GB 10.6 GB
Too big Get file →
Q3_K_L8.8 GB 11.2 GB
Too big Get file →
IQ4_XS9.1 GB 11.5 GB
Too big Get file →
Q4_09.6 GB 11.9 GB
Too big Get file →
IQ4_NL9.6 GB 11.9 GB
Too big Get file →
Q4_K_S9.6 GB 12.0 GB
Too big Get file →
Q4_K_M10.1 GB 12.5 GB
Too big Get file →
Q4_110.5 GB 12.9 GB
Too big Get file →
Q5_K_S11.5 GB 13.9 GB
Too big Get file →
Q5_K_M11.8 GB 14.2 GB
Too big Get file →
Q6_K13.6 GB 16.0 GB
Too big Get file →

What GPU do you need for The_Darkside 16.6B?

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: the best quant that fits is the main file (0.0 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_S (5.5 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (9.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.6 GB file, about 16.0 GB in use).

Which The_Darkside 16.6B quant should you choose?

Q4_K_M is the usual starting point for The_Darkside 16.6B: it balances file size and quality well. Here it is a 10.1 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters16.6B
Layers56
Trained context1,024,000 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilyThe
Licenseapache-2.0
Downloads (HF)135
Last updated2025-12-07

Frequently asked questions about The_Darkside 16.6B

How much VRAM does The_Darkside 16.6B need?

About 12.5 GB at Q4_K_M 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 The_Darkside 16.6B on an 8 GB GPU?

Yes, with IQ2_S: the 5.5 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of The_Darkside 16.6B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.9 GB, IQ1_M is 4.2 GB, IQ2_XXS is 4.8 GB, IQ2_XS is 5.2 GB, IQ2_S is 5.5 GB and 19 more.

What context length does The_Darkside 16.6B 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 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download The_Darkside 16.6B GGUF?

The files are on Hugging Face in the mradermacher/The_Darkside-16.6B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does The_Darkside 16.6B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More The models

All The →

Other medium models

All medium models →