Llama Guard 3 8B
Meta · dense · 8B parameters · 131,072 context
Parameters
8B
Context Window
128K tokens
Architecture
Dense
Best GPU
A30
Cheapest API
$0.03/M
Intelligence Brief
Llama Guard 3 8B is a 8B parameter DENSE model from Meta, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 131,072 token context window, it supports structured output, multilingual. The most cost-effective API deployment is via openrouter at $0.03/M output tokens. For self-hosted inference, A30 delivers optimal throughput at $332/month.
Provider pricing
2 providers · canonical: together| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| openrouter | $0.480 | $0.030 | cheapest output |
| togethercanonical | $0.200 | $0.200 | cheapest input |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- Llama Guard 3 1BLlama Guard · 1B—
- Code Llama 13BCode Llama · 13B$0.220/M out
- Code Llama 7BCode Llama · 7B$0.200/M out
- Llama 2 13BLlama 2 · 13B—
- Llama 2 7BLlama 2 · 7B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
16.0 GB
FP8 Weights
8.0 GB
INT4 Weights
4.0 GB
GPU Compatibility Matrix
Llama Guard 3 8B is compatible with 90% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
314.9 tok/s
Latency (ITL)
3.2ms
Est. TTFT
1ms
Cost/Month
$332
Cost/M Tokens
$0.40
BF16 · 1 GPU · vllm
100/100
score
Throughput
340.2 tok/s
Latency (ITL)
2.9ms
Est. TTFT
1ms
Cost/Month
$370
Cost/M Tokens
$0.41
BF16 · 1 GPU · vllm
100/100
score
Throughput
315.9 tok/s
Latency (ITL)
3.2ms
Est. TTFT
1ms
Cost/Month
$180
Cost/M Tokens
$0.22
Deployment Options
API Deployment
openrouter
$0.03/M
output tokens
Single GPU
A30
$332/mo
Min VRAM: 8 GB
Multi-GPU
RTX 3060 x2
190.4 tok/s
TP· $114/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openrouter | $0.48 | $0.03 | Cheapest |
| together | $0.20 | $0.20 | Low Input |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| openrouterBest Value | $0.48 | $0.03 | $3 |
| together | $0.20 | $0.20 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.25
via openrouter
Medium (2K tok)
$0.98
via openrouter
Long (8K tok)
$3.90
via openrouter
Performance Estimates
Throughput by GPU
VRAM Breakdown (A30, BF16)
Precision Impact
bf16
16.0 GB
weights/GPU
~314.9 tok/s
fp8
8.0 GB
weights/GPU
int4
4.0 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Llama Guard 3 8B
Self-Hosted Infrastructure
Similar Models
Aya 23 8B
8B params · dense
Quality: 50
from $0.60/M
DeepSeek R1 Distill 8B
8B params · dense
Quality: 88
from $0.20/M
InternLM3 8B
8B params · dense
Quality: 50
Llama 3 8B
8B params · dense
Quality: 63
from $0.04/M
Llama 3.3 8B
8B params · dense
Quality: 50
from $0.18/M
Frequently Asked Questions
How much VRAM does Llama Guard 3 8B need for inference?
Llama Guard 3 8B requires approximately 16.0 GB of VRAM at BF16 precision, 8.0 GB at FP8, or 4.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~1.00 GB).
What is the best GPU for Llama Guard 3 8B?
The top recommended GPU for Llama Guard 3 8B is the A30 using BF16 precision. It achieves approximately 314.9 tokens/sec at an estimated cost of $332/month ($0.40/M tokens). Score: 100/100.
How much does Llama Guard 3 8B inference cost?
Llama Guard 3 8B API inference starts from $0.48/M input tokens and $0.03/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.