FitMyLLM
HuggingFace/Dense

HuggingFaceSmolLM2 360M

Compact SmolLM for mobile and embedded AI applications.

chatTool Use
0.36B
Parameters
8K
Context length
6
Benchmarks
6
Quantizations
150K
HF downloads
Architecture
Dense
Released
2024-11-21
Layers
32
KV Heads
5
Head Dim
64
Family
smollm

Quantization Options

Context length:
QuantBitsVRAM @ 8KQuality
Q4_K_M4.89
0.9 GB
0.7 + 0.2 KV
good
Q5_K_S5.57
0.9 GB
0.7 + 0.2 KV
good
Q5_K_M5.7
0.9 GB
0.7 + 0.2 KV
good
Q6_K6.56
0.9 GB
0.8 + 0.2 KV
excellent
Q8_08.5
1.0 GB
0.9 + 0.2 KV
lossless
FP1616
1.4 GB
1.2 + 0.2 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run SmolLM2 360M now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run smollm:360m-base-v0.2-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for SmolLM2 360M

Build Hardware for SmolLM2 360M

Compact SmolLM for mobile and embedded AI applications.

Spec sheet

SmolLM2 360M — 0.36B Dense.

Specifications
Parameters
0.36B
Architecture
Dense Transformer
Context Length
8K tokens
Capabilities
chat
Release Date
2024-11-21
Provider
HuggingFace
Family
smollm
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.7 GB94%
Q5_K_S5.570.7 GB96%
Q5_K_M5.70.7 GB96%
Q6_K6.560.8 GB97%
Q8_08.50.9 GB100%
FP16161.2 GB100%
Benchmark scores
MMLU-PRO1.3
MATH1.5
IFEval38.4
BBH4.2
GPQA0.7
MUSR2.8
Run command

Run SmolLM2 360M locally with Ollama — needs 0.7 GB VRAM at Q4_K_M:

$ollama run smollm:360m
Compatible GPUs
30 @ Q4_K_M