SmolLM2 360M Instruct — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Incredibly lightweight. Runs on any device including old phones and embedded systems. Useful for on-device classification, simple Q&A, and keyword extraction where even 1B is too large.
SmolLM2 360M Instruct needs about 1 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 1.3 GB | ~381 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 1.3 GB | ~374 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 1.4 GB | ~363 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 1.4 GB | ~356 tok/s | Fits | |
| Q6_K 6.56 bpw | 1.4 GB | ~350 tok/s | Fits | |
| Q8_0 8.50 bpw | 1.5 GB | ~336 tok/s | Fits | |
| F16 16.00 bpw | 1.9 GB | ~292 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. SmolLM2 360M Instruct VRAM calculator →
Get SmolLM2 360M Instruct running
The cheapest catalogued GPU that runs SmolLM2 360M Instruct is the Intel Arc B570 (10 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run SmolLM2 360M Instruct
Install Ollama, then run:
ollama run smollm2:360mSpecifications
Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.
- Parameters
- 360 Million
- Context window
- 8,192
- Architecture
- Dense
- Provider
- Hugging Face
- Licence
- Apache 2.0
- Practical deployment
- Edge device (phone, SBC)
- Specified at
- Q4_K_M
- System RAM
- 2 GB
- Record updated
- 2024-11-20
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run SmolLM2 360M Instruct on my GPU?
Other SmolLM2 sizes
SmolLM2 360M Instruct — frequently asked questions
How much VRAM does SmolLM2 360M Instruct need?
About 1 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does SmolLM2 360M Instruct run on an RTX 4090 (24 GB)?
Yes. SmolLM2 360M Instruct needs about 1 GB at Q4_K_M, inside a 24 GB card, at an estimated 363 tokens/sec.
How do I run SmolLM2 360M Instruct locally?
Install Ollama and run `ollama run smollm2:360m`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does SmolLM2 come in?
SmolLM2 1.7B Instruct (2 GB), SmolLM2 360M Instruct (1 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.