SmolLM 360M
Hugging Face · dense · 0.36B parameters · 2,048 context
Parameters
0.36B
Context Window
2K tokens
Architecture
Dense
Best GPU
B200 SXM
Intelligence Brief
SmolLM 360M is a 0.36B parameter DENSE model from Hugging Face, featuring Grouped Query Attention (GQA) with 32 layers and 960 hidden dimensions. With a 2,048 token context window, it supports general text generation. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.
Architecture Details
Memory Requirements
BF16 Weights
0.7 GB
FP8 Weights
0.4 GB
INT4 Weights
0.2 GB
GPU Compatibility Matrix
SmolLM 360M is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4261
Cost/M Tokens
$0.46
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4271
Cost/M Tokens
$0.46
FP8 · 1 GPU · tensorrt-llm
83/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$6169
Cost/M Tokens
$0.67
Deployment Options
API Deployment
No API pricing available
Single GPU
B200 SXM
$4261/mo
Min VRAM: 0 GB
Multi-GPU
B200 SXM
3.5K tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, FP8)
Precision Impact
bf16
0.7 GB
weights/GPU
fp8
0.4 GB
weights/GPU
~3.5K tok/s
int4
0.2 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy SmolLM 360M
Self-Hosted Infrastructure
Similar Models
SmolLM 135M
0.135B params · dense
Quality: 50
BGE Large EN v1.5
0.335B params · dense
Quality: 50
from $0.01/M
NV EmbedQA E5 v5
0.33B params · dense
Quality: 50
from $0.01/M
NV Retriever v1
0.33B params · dense
Quality: 50
from $0.01/M
Whisper Small
0.244B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does SmolLM 360M need for inference?
SmolLM 360M requires approximately 0.7 GB of VRAM at BF16 precision, 0.4 GB at FP8, or 0.2 GB at INT4 quantization. Additional VRAM is needed for KV-cache (20480 bytes per token) and activations (~0.05 GB).
What is the best GPU for SmolLM 360M?
The top recommended GPU for SmolLM 360M is the B200 SXM using FP8 precision. It achieves approximately 3.5K tokens/sec at an estimated cost of $4261/month ($0.46/M tokens). Score: 83/100.
How much does SmolLM 360M inference cost?
SmolLM 360M inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.