SmolLM2 1.7B Instruct — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated November 20, 2024

Model library → SmolLM2 → SmolLM2 1.7B Instruct

The flagship SmolLM2 model. Shockingly capable for its size — runs in any browser via WebLLM or on any smartphone. Great for offline assistants, on-device privacy-preserving chat, and embedding AI in web apps.

SmolLM2 1.7B Instruct needs about 2 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.

Specifications

Parameters	1.7 Billion
Context window	8,192
Architecture	Dense
Provider	HuggingFace
Licence	Apache 2.0
Specified at	Q4_K_M
System RAM	4 GB
Record updated	2024-11-20

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	0.6 GB	3.0 GB	~247 tok/s (est.)	Fits comfortably
Q3_K_M	0.7 GB	3.1 GB	~234 tok/s (est.)	Fits comfortably
Q4_K_M	1.0 GB	3.4 GB	~214 tok/s (est.)	Fits comfortably
Q5_K_M	1.2 GB	3.6 GB	~203 tok/s (est.)	Fits comfortably
Q6_K	1.4 GB	3.8 GB	~194 tok/s (est.)	Fits comfortably
Q8_0	1.8 GB	4.2 GB	~175 tok/s (est.)	Fits comfortably
F16	3.4 GB	5.8 GB	~128 tok/s (est.)	Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the SmolLM2 1.7B Instruct VRAM calculator.

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

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.

Recommended GPU

The cheapest catalogued GPU that runs SmolLM2 1.7B Instruct is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Intel Arc B570 10GB

10 GB VRAM · 150 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

How to Run SmolLM2 1.7B Instruct

Install Ollama, then run:

ollama run smollm2:1.7b

Weights on Hugging Face: HuggingFaceTB/SmolLM2-1.7B-Instruct.

Best for: mobile, browser, edge devices, offline chat.

Can I Run SmolLM2 1.7B Instruct on My GPU?

Other SmolLM2 Sizes

SmolLM2 360M Instruct — about 1 GB VRAM at Q4_K_M

SmolLM2 1.7B Instruct — Frequently Asked Questions

How much VRAM does SmolLM2 1.7B Instruct need?

About 2 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 1.7B Instruct run on an RTX 4090 (24 GB)?

Yes. SmolLM2 1.7B Instruct needs about 2 GB at Q4_K_M, inside a 24 GB card, at an estimated 214 tokens/sec.

How do I run SmolLM2 1.7B Instruct locally?

Install Ollama and run `ollama run smollm2:1.7b`. 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.

← All SmolLM2 models | VRAM calculator | Check your own hardware