DA NeMona 21B Q6 K needs about 19.6 GB of memory at Q6_K (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
DA NeMona 21B Q6 K is a 20.4B-parameter Nemona model in GGUF format, quantized by SteelQuants. Its trained context length is 1000K tokens. The repository has 1 quant file, from 16.8 GB (Q6_K) to 16.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 16.8 GB | 19.6 GB | Too big | Get file → |
What GPU do you need for DA NeMona 21B Q6 K?
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 Q6_K (16.8 GB file, about 19.6 GB in use).
Which DA NeMona 21B Q6 K quant should you choose?
Q6_K (16.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DA NeMona 21B Q6 K
How much VRAM does DA NeMona 21B Q6 K need?
About 19.6 GB at Q6_K with an 8K context window. That is the 16.8 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 DA NeMona 21B Q6 K on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DA NeMona 21B Q6 K GGUF?
It depends on the quant: Q6_K is 16.8 GB.
What context length does DA NeMona 21B Q6 K 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 2.3 GB at 8K and 9.4 GB at 32K.
Where can I download DA NeMona 21B Q6 K GGUF?
The files are on Hugging Face in the SteelQuants/DA-NeMona-21B-Q6_K-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.