PixieZehirNano needs about 2.1 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.7 GB (Q2_K) to 3.7 GB (F16).
1.83B llama model with 16K context
PixieZehirNano is a 1.83B parameter llama model trained on 16384 tokens. It is released under the apache-2.0 license and available in multiple GGUF quantizations. The model supports text generation but has no vision capabilities.
Good at
- Text generation
- Prompt completion
- Lightweight inference
Limits
- No vision support
- Requires 16K context for full training context
- License is apache-2.0
Best for
- Chatbots on edge devices
- Quick prototyping
- Educational demos
Who it’s for. Developers and researchers who need a small llama model for local inference. The model is suitable for projects that require a lightweight, open‑source LLM without vision features.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.0 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.1 GB | Fits | Get file → | |
| Q5_K_S | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.5 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 1.9 GB | 3.0 GB | Fits | Get file → | |
| F16 | 3.7 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, Q2_K (0.71 GB file, 1.7 GB memory) is ideal. If more VRAM is available, Q3_K_S (0.82 GB, 1.8 GB) or Q4_K_S (1.06 GB, 2.1 GB) provide better quality. The F16 quant (3.66 GB, 4.7 GB) is for high‑end GPUs.
What GPU do you need for PixieZehirNano?
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 Q8_0 (1.9 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 4.7 GB in use).
Which PixieZehirNano quant should you choose?
Q4_K_M is the usual starting point for PixieZehirNano: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.9 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.
If memory is tight, the smallest file is Q2_K at 0.7 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
Source
Frequently asked questions about PixieZehirNano
How much VRAM does PixieZehirNano need?
About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.1 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 PixieZehirNano on an 8 GB GPU?
Yes, with F16: the 3.7 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of PixieZehirNano GGUF?
It depends on the quant: Q2_K is 0.7 GB, IQ3_XS is 0.8 GB, Q3_K_S is 0.8 GB, IQ3_S is 0.8 GB, IQ3_M is 0.9 GB, Q3_K_M is 0.9 GB and 9 more.
What context length does PixieZehirNano support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.0 GB at 16K.
Where can I download PixieZehirNano GGUF?
The files are on Hugging Face in the mradermacher/PixieZehirNano-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 PixieZehirNano 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 PixieZehirNano on 8 GB VRAM?
Yes, the Q2_K quant uses about 1.7 GB of VRAM at 8K context, fitting comfortably in 8 GB.
Does the model support image input?
No, PixieZehirNano is a text‑only model with no vision capabilities.
What license applies to the model?
The model is released under the apache-2.0 license.