Updated minutes ago
Llama 3.1 8B
Meta · dense · 8.03B parameters · 131,072 context
Quality65.0
Architecture Details
TypeDENSE
Total Parameters8.03B
Active Parameters8.03B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size128,256
Memory Requirements
BF16 Weights
16.1 GB
FP8 Weights
8.0 GB
INT4 Weights
4.0 GB
KV-Cache per Token131072 bytes
Activation Estimate1.00 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
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
313.7 tok/s
Cost/Month
$332
Cost/M Tokens
$0.40
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
338.9 tok/s
Cost/Month
$370
Cost/M Tokens
$0.42
RTX 3090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
314.7 tok/s
Cost/Month
$180
Cost/M Tokens
$0.22
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| groq | $0.05 | $0.08 | Cheapest |
| together | $0.18 | $0.18 | |
| fireworks | $0.20 | $0.20 |
Quality Benchmarks
MMLU69.4
HumanEval40.2
GSM8K79.6
MT-Bench78.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4