Datlas 2.5 needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.2 GB (F16).
Datlas 2.5 – a 72 M parameter Qwen2‑style causal LM
Datlas 2.5 is a 72 M parameter Qwen2‑shaped causal language model trained from scratch on a 260K‑row Web‑RAG corpus. It is available in multiple GGUF quantizations and supports reasoning and tool usage.
Good at
- Reasoning tasks
- Tool‑based interactions
- Web‑RAG agent integration
Limits
- Trained with 256‑token context
- No vision support
- Apache‑2.0 license
Best for
- Local reasoning agents
- Web‑search assistants
- Tool‑enabled workflows
Who it’s for. Developers building lightweight local agents that require reasoning and tool use. The model is suitable for environments with limited GPU memory and no need for vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q5_K_M (0.08 GB file, ~0.7 GB memory). For 16 GB VRAM, any of the 0.08 GB quants work; F16 (0.15 GB) offers higher precision if memory allows. Memory estimates are approximate.
What GPU do you need for Datlas 2.5?
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 F16 (0.2 GB file, about 0.8 GB in use).
Which Datlas 2.5 quant should you choose?
Q4_K_M is the usual starting point for Datlas 2.5: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.1 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 0.1 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 Datlas 2.5
How much VRAM does Datlas 2.5 need?
About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Datlas 2.5 on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Datlas 2.5 GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, IQ4_XS is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.
What context length does Datlas 2.5 support?
The GGUF header lists a trained context length of 256 tokens (256). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 256.
Where can I download Datlas 2.5 GGUF?
The files are on Hugging Face in the mradermacher/Datlas-2.5-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 Datlas 2.5 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 Datlas 2.5 on 8 GB VRAM?
Yes, the Q4_K_M or Q5_K_M quant files are 0.08 GB and require about 0.7 GB VRAM at 8k context.
Does Datlas 2.5 support vision?
No, the model has no vision capabilities.