zako pe needs about 2.9 GB of memory at Q6_K (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.1 GB (Q6_K) to 5.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.
Zako PE: a 2.52B‑parameter MiniCPM model for tool‑use tasks
Zako PE is a 2.52B‑parameter dense transformer based on openbmb/MiniCPM5-2B. It is quantized to Q6_K and BF16 for GGUF inference. The model supports a 131072‑token context window and is released under the Apache‑2.0 license.
Good at
- Tool use
- Long‑context reasoning
- Local deployment
Limits
- No vision support
- Requires 8k context for memory estimates
- No mixture of experts
Best for
- Local chatbot with tool integration
- Long‑form text analysis
- On‑device inference
Who it’s for. Developers building local LLM applications that need tool‑use capabilities and long‑context handling. The model is suitable for users who prefer an open‑source, Apache‑2.0 licensed solution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 2.1 GB | 2.9 GB | Fits | Get file → | |
| BF16 | 5.0 GB | 5.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q6_K quant file (2.07 GB, ~2.9 GB memory at 8k context). For higher precision and more RAM, use the BF16 file (5.04 GB, ~5.9 GB memory at 8k context).
What GPU do you need for zako pe?
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: the best quant that fits is Q6_K (2.1 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 5.9 GB in use).
Which zako pe quant should you choose?
Q6_K (2.1 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 zako pe
How much VRAM does zako pe need?
About 2.9 GB at Q6_K with an 8K context window. That is the 2.1 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 zako pe on an 8 GB GPU?
Yes, with BF16: the 5.0 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of zako pe GGUF?
It depends on the quant: Q6_K is 2.1 GB, BF16 is 5.0 GB.
What context length does zako pe support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.
Where can I download zako pe GGUF?
The files are on Hugging Face in the Johnny-Z/zako-pe repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does zako pe 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 Zako PE on 8 GB VRAM?
Yes, the Q6_K quant file uses about 2.9 GB of VRAM at 8k context, fitting within 8 GB.
Does Zako PE support vision tasks?
No, the model has no vision capabilities.