Smollm3-3B-128K needs about 3.0 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 1.0 GB (IQ2_XXS) to 6.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Smollm3-3B-128K: 3B parameter model with 128K token context
Smollm3-3B-128K is a 3B parameter decoder‑only transformer. It supports up to 128K tokens using YARN extrapolation. The model is fully open, licensed under Apache‑2.0, and designed for long‑context reasoning.
Good at
- Long‑context reasoning up to 128K tokens
- Hybrid reasoning with extended thinking mode
- Multilingual support for six languages
Limits
- Requires large VRAM for higher precision quants
- No vision or multimodal capabilities
- Context limited to 128K tokens
Best for
- Chat applications needing long context
- Research on reasoning tasks
- Fine‑tuning for domain‑specific long documents
Who it’s for. Developers and researchers who need a small, open model with extended context. Suitable for local deployment with llama.cpp or vllm.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 1.0 GB | 2.1 GB | Fits | Get file → | |
| IQ2_M | 1.2 GB | 2.3 GB | Fits | Get file → | |
| Q2_K | 1.3 GB | 2.4 GB | Fits | Get file → | |
| Q2_K_L | 1.3 GB | 2.4 GB | Fits | Get file → | |
| IQ3_XXS | 1.3 GB | 2.4 GB | Fits | Get file → | |
| Q2_K_XL | 1.3 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_XL | 1.6 GB | 2.7 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.8 GB | Fits | Get file → | |
| IQ4_NL | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_XL | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_XL | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.6 GB | Fits | Get file → | |
| Q6_K_XL | 2.8 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.4 GB | Fits | Get file → | |
| Q8_K_XL | 3.9 GB | 5.0 GB | Fits | Get file → | |
| BF16 | 6.2 GB | 7.3 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (≈3 GB file, 3 GB memory at 8 k context). For 12 GB VRAM, Q4_K_XL or Q5_K_S provide a balance of quality and memory. Higher precision quants such as Q6_K_XL or Q8_0 require more than 16 GB VRAM.
What GPU do you need for Smollm3-3B-128K?
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 Q6_K_XL (2.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_K_XL (3.9 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.2 GB file, about 7.3 GB in use).
Which Smollm3-3B-128K quant should you choose?
Q4_K_M is the usual starting point for Smollm3-3B-128K: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 IQ2_XXS at 1.0 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 Smollm3-3B-128K
How much VRAM does Smollm3-3B-128K need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Smollm3-3B-128K on an 8 GB GPU?
Yes, with BF16: the 6.2 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Smollm3-3B-128K GGUF?
It depends on the quant: IQ2_XXS is 1.0 GB, IQ2_M is 1.2 GB, Q2_K is 1.3 GB, Q2_K_L is 1.3 GB, IQ3_XXS is 1.3 GB, Q2_K_XL is 1.3 GB and 18 more.
What context length does Smollm3-3B-128K support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Smollm3-3B-128K GGUF?
The files are on Hugging Face in the unsloth/SmolLM3-3B-128K-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 Smollm3-3B-128K 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 Smollm3-3B-128K on 8 GB VRAM?
Yes, using a Q4_K_M or Q4_K_S quant will fit within 8 GB VRAM, with an estimated 3 GB memory usage at 8 k context.
Does the model support vision or multimodal inputs?
No, the model is a purely text‑based language model with no vision or multimodal capabilities.
What is the maximum context length I can use?
The model supports up to 128 k tokens using YARN extrapolation, with a trained context of 64 k tokens.