DA

DarkForest-20B-v3.0

DarkforestGGUF by mradermacherUpdated 2024-12-04
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant4.4 GB
Quick answer

DarkForest-20B-v3.0 needs about 22.9 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.4 GB (IQ1_S) to 16.4 GB (Q6_K).

DarkForest-20B-v3.0 – a 20B parameter Llama model with extensive quant options

DarkForest-20B-v3.0 is a 20 billion parameter Llama model. It supports 4096‑token context and is available in many GGUF quantizations. The model can generate mature content and follows instructions well.

Good at

  • Following complex instructions
  • Tracking multiple characters
  • Creative mature storytelling

Limits

  • No vision support
  • May produce NSFW content
  • License is other

Best for

  • Role‑playing games
  • Creative writing
  • Character dialogue generation

Who it’s for. Developers and writers who need a large Llama model for text generation. The model is suitable for mature audiences due to its ability to produce explicit content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.4 GB 10.1 GB
Too big Get file →
IQ1_M4.8 GB 10.5 GB
Too big Get file →
IQ2_XXS5.4 GB 11.1 GB
Too big Get file →
IQ2_XS5.9 GB 11.6 GB
Too big Get file →
IQ2_S6.4 GB 12.1 GB
Too big Get file →
IQ2_M6.9 GB 12.6 GB
Too big Get file →
Q2_K7.4 GB 13.1 GB
Too big Get file →
IQ3_XXS7.6 GB 13.3 GB
Too big Get file →
IQ3_XS8.2 GB 13.9 GB
Too big Get file →
IQ3_S8.7 GB 14.4 GB
Too big Get file →
Q3_K_S8.7 GB 14.4 GB
Too big Get file →
IQ3_M9.2 GB 14.9 GB
Too big Get file →
Q3_K_M9.7 GB 15.4 GB
Too big Get file →
Q3_K_L10.6 GB 16.3 GB
Too big Get file →
IQ4_XS10.7 GB 16.4 GB
Too big Get file →
Q4_011.3 GB 17.0 GB
Too big Get file →
Q4_K_S11.4 GB 17.1 GB
Too big Get file →
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_S13.8 GB 19.5 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q6_K16.4 GB 22.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.39 GB, 15.3 GB memory). For 12 GB VRAM, IQ2_M (6.9 GB, 17.8 GB memory) or Q2_K (7.42 GB, 18.3 GB memory). For 24 GB VRAM, Q5_K_M (14.16 GB, 25.1 GB memory) or Q6_K (16.4 GB, 27.3 GB memory). Memory estimates are approximate.

What GPU do you need for DarkForest-20B-v3.0?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ1_M (4.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (12.0 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).

Which DarkForest-20B-v3.0 quant should you choose?

Q4_K_M is the usual starting point for DarkForest-20B-v3.0: it balances file size and quality well. Here it is a 12.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.4 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
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
Licenseother
Downloads (HF)227
Last updated2024-12-04

Frequently asked questions about DarkForest-20B-v3.0

How much VRAM does DarkForest-20B-v3.0 need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 12.0 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 DarkForest-20B-v3.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DarkForest-20B-v3.0 GGUF?

It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.4 GB, IQ2_XS is 5.9 GB, IQ2_S is 6.4 GB, IQ2_M is 6.9 GB and 15 more.

What context length does DarkForest-20B-v3.0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download DarkForest-20B-v3.0 GGUF?

The files are on Hugging Face in the mradermacher/DarkForest-20B-v3.0-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 DarkForest-20B-v3.0 use?

Hugging Face lists the license as other. 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 DarkForest-20B-v3.0 on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant, which require about 15–16 GB of VRAM at 8 k context.

Does this model support vision?

No, the model has no vision capabilities.

Will it produce NSFW content?

Yes, the model can generate NSFW content and is intended for mature audiences.

Other GGUFs of DarkForest-20B-v3.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Darkforest models

All Darkforest →

Other medium models

All medium models →