DA

L3 DARKEST PLANET 16.5B

DarkestGGUF by DavidAUUpdated 2026-06-12
Download on Hugging Face
Parameters16.5B
Context8K
Layers71
Architecturellama
Smallest quant6.6 GB
Quick answer

L3 DARKEST PLANET 16.5B needs about 13.1 GB of memory at Q4_K_M (a 10.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 6.6 GB (Q2_K) to 18.6 GB (Q8_0).

L3 DARKEST PLANET 16.5B – a large Llama 3 model with 8192 token context

L3 DARKEST PLANET 16.5B is a 16.5 billion‑parameter Llama model with a maximum context of 8192 tokens. It is built on the Darkest family and uses the Brainstorm 40x adapter to expand the base 8B model. The model is released under the Apache‑2.0 license and supports role‑play tasks.

Good at

  • Detailed fiction writing
  • Role‑play scenarios
  • Complex narrative generation

Limits

  • Requires Llama3 template
  • No vision support
  • Class 3/4 model – needs specific sampler settings

Best for

  • Creative writing projects
  • Interactive storytelling
  • Character development scripts

Who it’s for. Developers and writers who need a large, detailed LLM for narrative tasks. The model is suitable for applications that can handle its 8192‑token context and the required sampler configuration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.6 GB 9.4 GB
Too big Get file →
Q3_K_S7.5 GB 10.4 GB
Too big Get file →
Q2_K7.8 GB 10.7 GB
Too big Get file →
Q2_K7.8 GB 10.7 GB
Too big Get file →
Q3_K_M8.3 GB 11.2 GB
Too big Get file →
Q4_09.4 GB 12.3 GB
Too big Get file →
Q4_09.4 GB 12.3 GB
Too big Get file →
Q4_09.4 GB 12.3 GB
Too big Get file →
IQ4_XS9.5 GB 12.4 GB
Too big Get file →
Q4_K_S9.7 GB 12.6 GB
Too big Get file →
Q4_K_M10.2 GB 13.1 GB
Too big Get file →
IQ4_XS10.5 GB 13.3 GB
Too big Get file →
IQ4_XS10.5 GB 13.3 GB
Too big Get file →
Q5_K_S11.6 GB 14.5 GB
Too big Get file →
Q5_K_M11.9 GB 14.8 GB
Too big Get file →
Q6_K13.8 GB 16.7 GB
Too big Get file →
Q6_K14.8 GB 17.7 GB
Too big Get file →
Q6_K14.8 GB 17.7 GB
Too big Get file →
Q8_017.6 GB 20.5 GB
Too big Get file →
Q8_018.6 GB 21.4 GB
Too big Get file →
Q8_018.6 GB 21.4 GB
Too big Get file →

For 8 GB VRAM use Q2_K (6.56 GB file, ~9.4 GB VRAM at 8k context). For 12 GB VRAM use Q4_0 (9.45 GB file, ~12.3 GB VRAM). For 20 GB VRAM use Q8_0 (17.58 GB file, ~20.5 GB VRAM). Memory estimates are approximate.

What GPU do you need for L3 DARKEST PLANET 16.5B?

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 Q3_K_M (8.3 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (11.9 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 21.4 GB in use).

Which L3 DARKEST PLANET 16.5B quant should you choose?

Q4_K_M is the usual starting point for L3 DARKEST PLANET 16.5B: it balances file size and quality well. Here it is a 10.2 GB file.

The Q8_0 file is 17.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 6.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters16.5B
Layers71
Trained context8,192 tokens
KV cache (fp16)284 KB per token

Source

Quantized byDavidAU
FamilyDarkest
Licenseapache-2.0
Downloads (HF)6,675
Last updated2026-06-12

Frequently asked questions about L3 DARKEST PLANET 16.5B

How much VRAM does L3 DARKEST PLANET 16.5B need?

About 13.1 GB at Q4_K_M with an 8K context window. That is the 10.2 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 L3 DARKEST PLANET 16.5B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of L3 DARKEST PLANET 16.5B GGUF?

It depends on the quant: Q2_K is 6.6 GB, Q3_K_S is 7.5 GB, Q2_K is 7.8 GB, Q2_K is 7.8 GB, Q3_K_M is 8.3 GB, Q4_0 is 9.4 GB and 15 more.

What context length does L3 DARKEST PLANET 16.5B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.4 GB at 8K and 2.4 GB at 8K.

Where can I download L3 DARKEST PLANET 16.5B GGUF?

The files are on Hugging Face in the DavidAU/L3-DARKEST-PLANET-16.5B-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 L3 DARKEST PLANET 16.5B 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.

Can I run L3 DARKEST PLANET 16.5B on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 9.4 GB VRAM at 8k context. It is close to the limit, so a small batch size is recommended.

Does this model support image inputs?

No, the model has no vision capabilities. It only processes text.

What sampler settings are required for best performance?

The model is Class 3/4; it needs specific sampler and advanced sampler settings as detailed in the provided documentation.

Other GGUFs of L3-DARKEST-PLANET-16.5B

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More Darkest models

All Darkest →

Other medium models

All medium models →