Skip to content
Updated minutes ago
HuggingFace

SmolLM2 1.7B

Hugging Face · dense · 1.7B parameters · 8,192 context

Quality
50.0

Architecture Details

TypeDENSE
Total Parameters1.7B
Active Parameters1.7B
Layers24
Hidden Dimension2,048
Attention Heads32
KV Heads32
Head Dimension64
Vocab Size49,152

Memory Requirements

BF16 Weights

3.4 GB

FP8 Weights

1.7 GB

INT4 Weights

0.8 GB

KV-Cache per Token196608 bytes
Activation Estimate0.30 GB

Fits on (single-node)

B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16

GPU Recommendations

A4000optimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

675.9 tok/s

Cost/Month

$161

Cost/M Tokens

$0.09

Use this config →
RTX 4080optimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

1.1K tok/s

Cost/Month

$304

Cost/M Tokens

$0.11

Use this config →
RTX 4070 Tioptimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

760.4 tok/s

Cost/Month

$237

Cost/M Tokens

$0.12

Use this config →

API Pricing Comparison

No API pricing data available for this model.

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgiollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models