SM

Smollm3-3B

SmolLMGGUF by unslothUpdated 2025-07-08
Download on Hugging Face
Parameters3.08B
Context64K
Layers36
Architecturesmollm3
Smallest quant1.0 GB
Quick answer

Smollm3-3B 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: 3B parameter open model with long context and hybrid reasoning

Smollm3-3B is a 3 billion‑parameter decoder‑only transformer. It supports up to 128 k tokens of context and is optimized for hybrid reasoning. The model is fully open under the Apache‑2.0 license.

Good at

  • Hybrid reasoning with extended thinking
  • Long‑context processing up to 128k tokens
  • Multilingual support for six languages

Limits

  • Requires at least 8 k context for memory estimates
  • No vision or multimodal capabilities
  • Large memory for higher‑quality quants

Best for

  • Developing chatbots with reasoning traces
  • Fine‑tuning on domain‑specific text
  • Running on GPUs with 8 GB VRAM using low‑bit quants

Who it’s for. Engineers and researchers building lightweight LLM applications who need strong reasoning and long‑context handling. The model is suitable for developers who prefer open weights and full training transparency.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS1.0 GB 2.1 GB
Fits Get file →
IQ2_M1.2 GB 2.3 GB
Fits Get file →
Q2_K1.3 GB 2.4 GB
Fits Get file →
Q2_K_L1.3 GB 2.4 GB
Fits Get file →
IQ3_XXS1.3 GB 2.4 GB
Fits Get file →
Q2_K_XL1.3 GB 2.4 GB
Fits Get file →
Q3_K_S1.4 GB 2.5 GB
Fits Get file →
Q3_K_M1.6 GB 2.7 GB
Fits Get file →
Q3_K_XL1.6 GB 2.7 GB
Fits Get file →
IQ4_XS1.7 GB 2.8 GB
Fits Get file →
IQ4_NL1.8 GB 2.9 GB
Fits Get file →
Q4_01.8 GB 2.9 GB
Fits Get file →
Q4_K_S1.8 GB 2.9 GB
Fits Get file →
Q4_K_M1.9 GB 3.0 GB
Fits Get file →
Q4_K_XL1.9 GB 3.0 GB
Fits Get file →
Q4_12.0 GB 3.1 GB
Fits Get file →
Q5_K_S2.2 GB 3.3 GB
Fits Get file →
Q5_K_M2.2 GB 3.3 GB
Fits Get file →
Q5_K_XL2.2 GB 3.3 GB
Fits Get file →
Q6_K2.5 GB 3.6 GB
Fits Get file →
Q6_K_XL2.8 GB 3.9 GB
Fits Get file →
Q8_03.3 GB 4.4 GB
Fits Get file →
Q8_K_XL3.9 GB 5.0 GB
Fits Get file →
BF166.2 GB 7.3 GB
Tight Get file →

For 8 GB VRAM, use IQ4_XS (1.72 GB file, ~2.8 GB RAM) or Q4_K_S (1.82 GB file, ~2.9 GB RAM). If 12 GB VRAM is available, Q4_K_M (1.92 GB file, ~3 GB RAM) offers better quality. Higher quants such as Q6_K_XL require >3.9 GB RAM and are best on larger GPUs.

What GPU do you need for Smollm3-3B?

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 quant should you choose?

Q4_K_M is the usual starting point for Smollm3-3B: 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

Architecturesmollm3
Parameters3.08B
Layers36
Trained context65,536 tokens
KV cache (fp16)72 KB per token

Source

Quantized byunsloth
FamilySmolLM
Licenseapache-2.0
Downloads (HF)14,390
Last updated2025-07-08

Frequently asked questions about Smollm3-3B

How much VRAM does Smollm3-3B 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 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 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 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). 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 GGUF?

The files are on Hugging Face in the unsloth/SmolLM3-3B-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 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 on 8 GB VRAM?

Yes, with a low‑bit quant such as IQ4_XS or Q4_K_S the estimated VRAM usage is below 8 GB.

Does the model support vision?

No, Smollm3-3B is a text‑only language model.

What is the maximum context length?

The model is trained for 64k tokens and supports up to 128k tokens using YARN extrapolation.

Other GGUFs of SmolLM3-3B

Similar models

Browse all →

More from unsloth

All by unsloth →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →