Naphula__DarkForest 20B v2.0 Erebus Edition 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 6 quants, from 12.0 GB (Q4_K_M) to 40.0 GB (F16).
Naphula__DarkForest 20B v2.0 Erebus Edition is a 20B-parameter Llama model in GGUF format, quantized by Naphula. Its trained context length is 4K tokens. The repository has 6 quant files, from 12.0 GB (Q4_K_M) to 40.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 12.0 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_M | 14.4 GB | 20.1 GB | Too big | Get file → | |
| Q6_K | 16.4 GB | 22.1 GB | Too big | Get file → | |
| Q8_0 | 21.2 GB | 26.9 GB | Too big | Get file → | |
| Q8_K_XL | 22.9 GB | 28.6 GB | Too big | Get file → | |
| F16 | 40.0 GB | 45.7 GB | Too big | Get file → |
What GPU do you need for Naphula__DarkForest 20B v2.0 Erebus Edition?
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: no quant fits at an 8K context.
- 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).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (22.9 GB file, about 33.8 GB in use).
Which Naphula__DarkForest 20B v2.0 Erebus Edition quant should you choose?
Q4_K_M is the usual starting point for Naphula__DarkForest 20B v2.0 Erebus Edition: it balances file size and quality well. Here it is a 12.0 GB file.
The Q8_0 file is 21.2 GB, about 1.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Naphula__DarkForest 20B v2.0 Erebus Edition
How much VRAM does Naphula__DarkForest 20B v2.0 Erebus Edition 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 Naphula__DarkForest 20B v2.0 Erebus Edition on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Naphula__DarkForest 20B v2.0 Erebus Edition GGUF?
It depends on the quant: Q4_K_M is 12.0 GB, Q5_K_M is 14.4 GB, Q6_K is 16.4 GB, Q8_0 is 21.2 GB, Q8_K_XL is 22.9 GB, F16 is 40.0 GB.
What context length does Naphula__DarkForest 20B v2.0 Erebus Edition 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 Naphula__DarkForest 20B v2.0 Erebus Edition GGUF?
The files are on Hugging Face in the Naphula/DarkForest-20B-v2.0-Erebus-Edition-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 Naphula__DarkForest 20B v2.0 Erebus Edition use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.