deepseek pikaqu33 needs about 4.5 GB of memory at Q4_K (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU.
deepseek pikaqu33 is a 1.78B-parameter DeepSeek model in GGUF format, quantized by 1dfs6df. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.6 GB (Q4_K) to 3.6 GB (Q4_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 3.6 GB | 4.5 GB | Fits | Get file → |
What GPU do you need for deepseek pikaqu33?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K (3.6 GB file, about 4.5 GB in use).
Which deepseek pikaqu33 quant should you choose?
Q4_K (3.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about deepseek pikaqu33
How much VRAM does deepseek pikaqu33 need?
About 4.5 GB at Q4_K with an 8K context window. That is the 3.6 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 deepseek pikaqu33 on an 8 GB GPU?
Yes, with Q4_K: the 3.6 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of deepseek pikaqu33 GGUF?
It depends on the quant: Q4_K is 3.6 GB.
What context length does deepseek pikaqu33 support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download deepseek pikaqu33 GGUF?
The files are on Hugging Face in the 1dfs6df/deepseek_pikaqu33 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.