Updated minutes ago
Gemma 3 12B
Google · dense · 12B parameters · 131,072 context
Quality71.0
Architecture Details
TypeDENSE
Total Parameters12B
Active Parameters12B
Layers48
Hidden Dimension3,072
Attention Heads32
KV Heads16
Head Dimension128
Vocab Size262,144
Memory Requirements
BF16 Weights
24.0 GB
FP8 Weights
12.0 GB
INT4 Weights
6.0 GB
KV-Cache per Token393216 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
A100 40GB SXMoptimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
349.9 tok/s
Cost/Month
$807
Cost/M Tokens
$0.88
RTX A6000optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
172.8 tok/s
Cost/Month
$465
Cost/M Tokens
$1.02
A40optimal
BF16 · 1 GPU · vllm
95/100
score
Throughput
156.6 tok/s
Cost/Month
$399
Cost/M Tokens
$0.97
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| $0.05 | $0.10 | Cheapest | |
| together | $0.15 | $0.15 |
Quality Benchmarks
MMLU74.0
HumanEval44.0
GSM8K78.0
MT-Bench80.0
Capabilities
Features
✓ Tool Use✓ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4