SmallThinker 21BA3B Instruct needs about 14.5 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.1 GB to 17.7 GB (Q6_K).
SmallThinker 21BA3B Instruct – a 21.5B Mixture‑of‑Experts model for local deployment
SmallThinker 21BA3B Instruct is a 21.5B parameter Mixture‑of‑Experts language model. It is designed for on‑device inference with a 16384 token context window. The model is released under the Apache‑2.0 license.
Good at
- Tool‑use instructions
- Local inference on limited hardware
- Large context handling
Limits
- No vision support
- Requires 8‑k context for memory estimates
- Mixture‑of‑Experts may increase latency
Best for
- Developing lightweight chatbots
- Running on edge devices
- Fine‑tuning for specific tasks
Who it’s for. Developers and researchers who need a large‑scale language model that can run locally on devices with limited GPU memory. The model is suitable for applications requiring private, low‑latency inference without cloud dependency.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 4.6 GB | 6.0 GB | Fits | Get file → | |
| IQ1_M | 5.1 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XXS | 5.9 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XS | 6.5 GB | 7.8 GB | Tight | Get file → | |
| IQ2_S | 6.7 GB | 8.0 GB | Too big | Get file → | |
| IQ2_M | 7.3 GB | 8.6 GB | Too big | Get file → | |
| Q2_K_S | 7.5 GB | 8.9 GB | Too big | Get file → | |
| Q2_K | 8.0 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XXS | 8.4 GB | 9.8 GB | Too big | Get file → | |
| IQ3_XS | 9.0 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_S | 9.4 GB | 10.8 GB | Too big | Get file → | |
| IQ3_S | 9.4 GB | 10.8 GB | Too big | Get file → | |
| IQ3_M | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q3_K_M | 10.4 GB | 11.8 GB | Too big | Get file → | |
| Q3_K_L | 11.3 GB | 12.6 GB | Too big | Get file → | |
| IQ4_XS | 11.6 GB | 13.0 GB | Too big | Get file → | |
| Q4_0 | 12.3 GB | 13.7 GB | Too big | Get file → | |
| Q4_K_S | 12.3 GB | 13.7 GB | Too big | Get file → | |
| Q4_K_M | 13.1 GB | 14.5 GB | Too big | Get file → | |
| Q4_1 | 13.6 GB | 14.9 GB | Too big | Get file → | |
| Q5_K_S | 14.9 GB | 16.2 GB | Too big | Get file → | |
| Q5_K_M | 15.3 GB | 16.7 GB | Too big | Get file → | |
| Q6_K | 17.7 GB | 19.0 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (13.09 GB file, ~14.5 GB memory at 8‑k context). For 16‑GB VRAM, Q5_K_M (15.31 GB file, ~16.7 GB memory) is a good balance. For 32‑GB VRAM, Q6_K (17.68 GB file, ~19 GB memory) provides the highest capacity.
What GPU do you need for SmallThinker 21BA3B 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 the main file (0.1 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_S (4.6 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_S (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (10.4 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_1 (13.6 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (17.7 GB file, about 19.0 GB in use).
Which SmallThinker 21BA3B Instruct quant should you choose?
Q4_K_M is the usual starting point for SmallThinker 21BA3B Instruct: it balances file size and quality well. Here it is a 13.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SmallThinker 21BA3B Instruct
How much VRAM does SmallThinker 21BA3B Instruct need?
About 14.5 GB at Q4_K_M with an 8K context window. That is the 13.1 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 SmallThinker 21BA3B Instruct on an 8 GB GPU?
Yes, with IQ2_S: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmallThinker 21BA3B Instruct GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 4.6 GB, IQ1_M is 5.1 GB, IQ2_XXS is 5.9 GB, IQ2_XS is 6.5 GB, IQ2_S is 6.7 GB and 18 more.
What context length does SmallThinker 21BA3B Instruct support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.9 GB at 8K and 1.7 GB at 16K.
Where can I download SmallThinker 21BA3B Instruct GGUF?
The files are on Hugging Face in the mradermacher/SmallThinker-21BA3B-Instruct-i1-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 21BA3B 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 21BA3B Instruct on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 14.5 GB of VRAM at 8‑k context, which fits within an 8‑GB GPU with some overhead.
Does the model support vision tasks?
No, SmallThinker 21BA3B Instruct does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.