Skip to content
Updated minutes ago
Google

Gemma 3 12B

Google · dense · 12B parameters · 131,072 context

Quality
71.0

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

Use this config →
RTX A6000optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

172.8 tok/s

Cost/Month

$465

Cost/M Tokens

$1.02

Use this config →
A40optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

156.6 tok/s

Cost/Month

$399

Cost/M Tokens

$0.97

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
google$0.05$0.10
Cheapest
together$0.15$0.15

Quality Benchmarks

MMLU
74.0
HumanEval
44.0
GSM8K
78.0
MT-Bench
80.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models