dgpl experimental 1 needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.3 GB (Q4_K_M) to 1.1 GB (F16).
DGPL Experimental 1 – a lightweight 0.55B reasoning prototype
DGPL Experimental 1 is a 0.55 billion parameter model focused on reasoning tasks. It supports a native 1‑million token context and is designed for edge deployment with LoopSpec speculative decoding. The model is experimental and not intended for production critical use.
Good at
- Reasoning and logical deduction
- Basic arithmetic and physics derivations
- Linux administration tasks
Limits
- Experimental prototype, not for production
- Requires non‑zero sampling penalties to avoid repetition
- No vision or multimodal support
Best for
- Edge inference on consumer GPUs
- Rapid prototyping of reasoning models
- Testing LoopSpec speculative decoding
Who it’s for. Developers and researchers interested in ultra‑lightweight edge Mixture‑of‑Experts research. The model is suitable for experimentation and proof‑of‑concept deployments rather than production workloads.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| F16 | 1.1 GB | 1.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_M (≈0.9 GB memory at 8k context). If 12 GB VRAM is available, Q6_K or Q8_0 can be used (≈1–1.2 GB). The F16 quant requires about 1.8 GB memory and is best for higher‑precision inference on larger GPUs.
What GPU do you need for dgpl experimental 1?
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: the best quant that fits is F16 (1.1 GB file, about 1.8 GB in use).
Which dgpl experimental 1 quant should you choose?
Q4_K_M is the usual starting point for dgpl experimental 1: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.6 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 dgpl experimental 1
How much VRAM does dgpl experimental 1 need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 dgpl experimental 1 on an 8 GB GPU?
Yes, with F16: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dgpl experimental 1 GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q5_K_M is 0.4 GB, Q6_K is 0.4 GB, Q8_0 is 0.6 GB, F16 is 1.1 GB.
Where can I download dgpl experimental 1 GGUF?
The files are on Hugging Face in the dgpl/dgpl-experimental-1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does dgpl experimental 1 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 DGPL Experimental 1 on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations which use approximately 0.9 GB of VRAM at 8k context.
What sampling penalties are required?
Set repeat_penalty 1.25, presence_penalty 0.5, frequency_penalty 0.4, repeat_last_n 256 to avoid repetition loops.
Is this model suitable for production?
No, it is an experimental prototype and not recommended for production critical use.