SmallThinker 4BA0.6B Instruct needs about 3.4 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.7 GB (Q2_K) to 8.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.
SmallThinker 4BA0.6B Instruct – a lightweight, Mixture‑of‑Experts LLM for local deployment
SmallThinker 4BA0.6B Instruct is a 4.27 billion‑parameter model built for on‑device inference. It supports a 32768‑token context window and is trained with a two‑level sparse MoE architecture. The model is released under the apache‑2.0 license.
Good at
- Tool‑use tasks
- Local inference on modest GPUs
- Efficient memory usage
Limits
- No vision support
- Requires GPU for best performance
- Limited to 32768‑token context
Best for
- Chatbots on edge devices
- Code generation with tool calls
- Rapid prototyping of LLM features
Who it’s for. Developers and researchers who need a small, efficient LLM that can run on local hardware without cloud access. The model is suitable for projects that require tool‑use capabilities and a large context window in a compact footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 2.4 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_S | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 3.5 GB | 4.3 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 5.3 GB | Fits | Get file → | |
| F16 | 8.5 GB | 9.3 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (file size 2.63 GB, estimated 3.4 GB memory) is a good balance. If memory is tighter, Q3_K_M (2.12 GB, 2.9 GB memory) or Q3_K_S (1.94 GB, 2.7 GB memory) can be used. For the lowest memory usage, Q2_K (1.66 GB, 2.4 GB memory) is available but may have reduced quality.
What GPU do you need for SmallThinker 4BA0.6B Instruct?
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 Q5_K_M (3.1 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.3 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.5 GB file, about 9.3 GB in use).
Which SmallThinker 4BA0.6B Instruct quant should you choose?
Q4_K_M is the usual starting point for SmallThinker 4BA0.6B Instruct: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.5 GB, about 1.7 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 1.7 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 SmallThinker 4BA0.6B Instruct
How much VRAM does SmallThinker 4BA0.6B Instruct need?
About 3.4 GB at Q4_K_M with an 8K context window. That is the 2.6 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 SmallThinker 4BA0.6B Instruct on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmallThinker 4BA0.6B Instruct GGUF?
It depends on the quant: Q2_K is 1.7 GB, Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.3 GB, IQ4_XS is 2.4 GB, Q4_K_S is 2.5 GB and 6 more.
What context length does SmallThinker 4BA0.6B Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.
Where can I download SmallThinker 4BA0.6B Instruct GGUF?
The files are on Hugging Face in the mradermacher/SmallThinker-4BA0.6B-Instruct-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 SmallThinker 4BA0.6B Instruct 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 SmallThinker 4BA0.6B Instruct on 8 GB VRAM?
Yes, the Q4_K_M quant requires approximately 3.4 GB of VRAM at 8k context, which fits within an 8 GB GPU.
Does the model support image inputs?
No, SmallThinker 4BA0.6B Instruct does not include vision capabilities.
What license applies to this model?
The model is distributed under the apache‑2.0 license.