TinyBalls 110M V1 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). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
TinyBalls 110M V1 – a small LLaMA‑style instruct model
TinyBalls 110M V1 is a 113M‑parameter LLaMA‑style model trained from scratch on 2B tokens and fine‑tuned for chat and tool use. It supports reasoning and tool calling. The model is released under the MIT license.
Good at
- Chat and tool‑calling
- Reasoning tasks
- Lightweight inference
Limits
- No vision support
- Small context length of 32768 tokens
- Requires at least 0.7 GB VRAM for 8K context
Best for
- Embedded chat assistants
- Tool‑enabled agents
- Low‑resource inference
Who it’s for. Developers building lightweight chat or tool‑calling agents who need a small, open‑source model. The model is suitable for environments with limited GPU memory and for use cases that do not require vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.08 GB file, ~0.7 GB VRAM). For 4 GB VRAM, use Q3_K_S (0.07 GB file, ~0.7 GB VRAM). For 2 GB VRAM, use Q2_K (0.06 GB file, ~0.7 GB VRAM). Estimates are approximate.
What GPU do you need for TinyBalls 110M V1?
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 TinyBalls 110M V1 quant should you choose?
Q4_K_M is the usual starting point for TinyBalls 110M V1: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.6 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 TinyBalls 110M V1
How much VRAM does TinyBalls 110M V1 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 TinyBalls 110M V1 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 TinyBalls 110M V1 GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, IQ4_XS is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.
What context length does TinyBalls 110M V1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download TinyBalls 110M V1 GGUF?
The files are on Hugging Face in the mradermacher/TinyBalls-110M-V1-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 TinyBalls 110M V1 use?
Hugging Face lists the license as mit. 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 TinyBalls 110M V1 on 8 GB VRAM?
Yes. The Q4_K_M quant uses about 0.7 GB VRAM at 8K context, well within 8 GB.
Does the model support vision?
No. The model has no vision capabilities.
What license does the model use?
The model is released under the MIT license.