Skip to content
Updated minutes ago
Google

Gemma 2 9B

Google · dense · 9.2B parameters · 8,192 context

Quality
68.0

Architecture Details

TypeDENSE
Total Parameters9.2B
Active Parameters9.2B
Layers42
Hidden Dimension3,584
Attention Heads16
KV Heads8
Head Dimension256
Vocab Size256,000

Memory Requirements

BF16 Weights

18.4 GB

FP8 Weights

9.2 GB

INT4 Weights

4.6 GB

KV-Cache per Token344064 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

RTX 5090optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

473.3 tok/s

Cost/Month

$845

Cost/M Tokens

$0.68

Use this config →
V100 32GBoptimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

91.7 tok/s

Cost/Month

$180

Cost/M Tokens

$0.75

Use this config →
Instinct MI100optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

110.8 tok/s

Cost/Month

$380

Cost/M Tokens

$1.30

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
deepinfra$0.10$0.10
Cheapest
together$0.20$0.20

Quality Benchmarks

MMLU
71.3
HumanEval
40.0
GSM8K
76.0
MT-Bench
78.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models