Skip to content
localmodel.run

Text model · SmolLM2

SmolLM2 135M requirements

SmolLM2 family · 0.135B params · released 2024-11-02 · 2.6M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseApache-2.0· Commercial OK↓ 1.3M/mo♥ 348on HuggingFace
Q4_K_M
0.105 GB
Q8_0
0.145 GB
Total @ Q4 (4k)
~1 GB
Context
2 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K0.1 GB est
Q3_K_M0.1 GB est
Q4_K_M (default)0.105 GB
Q5_K_M0.1 GB est
Q6_K0.1 GB est
Q8_00.145 GB
FP160.3 GB est

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

Run it

Ollama
$ ollama run smollm2:135m
llama.cpp
$ llama-cli -hf bartowski/SmolLM2-135M-Instruct-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/SmolLM2-135M-Instruct-GGUF

Which devices can run SmolLM2 135M?

FAQ

How much VRAM or RAM does SmolLM2 135M need?

At Q4_K_M, SmolLM2 135M needs about 1 GB (weights ~0.105 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~1 GB.

Can SmolLM2 135M run on a laptop?

Yes, SmolLM2 135M fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use SmolLM2 135M commercially?

Yes. SmolLM2 135M is licensed Apache-2.0, which permits commercial use.

Hugging Face's smallest SLM. 135M params, fits in ~105MB at Q4_K_M. Designed for microcontrollers and on-device inference. Trained on 2T tokens (FineWeb-Edu, DCLM, The Stack).

Sources

Memory figures are estimates. See methodology.