zubr tiny 2b needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.8 GB (Q2_K_L) to 1.3 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Lightweight 2B‑parameter Qwen 3.5 model for local inference
zubr‑tiny‑2b is a 1.88‑billion‑parameter conversational model based on Qwen 3.5. It is fine‑tuned for reasoning and tool use while keeping a small hardware footprint. The model is optimized for fast local inference on consumer‑grade GPUs and CPUs.
Good at
- Reasoning
- Tool usage
- Instruction following
Limits
- No vision support
- Limited to 262144 context tokens
- Requires Apache‑2.0 license
Best for
- Rapid prototyping
- Task‑specific fine‑tuning
- Research demos
Who it’s for. Developers and researchers who need a compact, fast‑running Qwen‑based model for local deployment. It is suitable for laptops, edge devices, and low‑budget cloud instances.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_L | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q2_K_L (0.84 GB, 1.7 GB RAM) or IQ2_M (0.87 GB, 1.8 GB RAM). For 4 GB VRAM, Q2_K_L is the smallest option. Larger VRAM allows Q4_K_M (1.27 GB, 2.2 GB RAM). Memory estimates are approximate.
What GPU do you need for zubr tiny 2b?
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 Q4_K_M (1.3 GB file, about 2.2 GB in use).
Which zubr tiny 2b quant should you choose?
Q4_K_M is the usual starting point for zubr tiny 2b: it balances file size and quality well. Here it is a 1.3 GB file.
If memory is tight, the smallest file is Q2_K_L at 0.8 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 zubr tiny 2b
How much VRAM does zubr tiny 2b need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 zubr tiny 2b on an 8 GB GPU?
Yes, with Q4_K_M: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of zubr tiny 2b GGUF?
It depends on the quant: Q2_K_L is 0.8 GB, IQ2_M is 0.9 GB, Q4_K_M is 1.3 GB.
What context length does zubr tiny 2b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download zubr tiny 2b GGUF?
The files are on Hugging Face in the alekringtonnn-ai/zubr-tiny-2b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does zubr tiny 2b 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 zubr‑tiny‑2b on 8 GB VRAM?
Yes, the Q2_K_L and IQ2_M quantizations fit within 8 GB VRAM and use about 1.7–1.8 GB RAM.
Can I run it on 4 GB VRAM?
Yes, Q2_K_L fits within 4 GB VRAM and uses about 1.7 GB RAM.
Does the model support vision?
No, zubr‑tiny‑2b is a text‑only model with no vision capability.