Skip to content
localmodel.run

Text model · SmolLM3

SmolLM3 3B requirements

SmolLM3 family · 3B params · released Jul 2025. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseApache-2.0· Commercial OK↓ 374.5K/mo♥ 971on HuggingFace
Q4_K_M
1.78 GB
Q8_0
3.05 GB
Total @ Q4 (4k)
~3 GB
Context
128 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K1.3 GB est
Q3_K_M1.5 GB est
Q4_K_M (default)1.78 GB
Q5_K_M2.1 GB est
Q6_K2.5 GB est
Q8_03.05 GB
FP166 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

llama.cpp
$ llama-cli -hf unsloth/SmolLM3-3B-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/SmolLM3-3B-GGUF

Which devices can run SmolLM3 3B?

FAQ

How much VRAM or RAM does SmolLM3 3B need?

At Q4_K_M, SmolLM3 3B needs about 3 GB (weights ~1.78 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~4.3 GB.

Can SmolLM3 3B run on a laptop?

Yes, SmolLM3 3B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use SmolLM3 3B commercially?

Yes. SmolLM3 3B is licensed Apache-2.0, which permits commercial use.

Hugging Face SmolLM3 3B, long-context small model. Q4_K_M and Q8_0 sizes from the unsloth GGUF repo.

Sources

Memory figures are estimates. See methodology.