Skip to content
Updated minutes ago
Google

Gemini 1.5 Flash

Google · moe · 50B parameters · 1,048,576 context

Quality
75.0

Architecture Details

TypeMOE
Total Parameters50B
Active Parameters12B
Layers40
Hidden Dimension5,120
Attention Heads40
KV Heads8
Head Dimension128
Vocab Size256,000
Total Experts8
Active Experts2

Memory Requirements

BF16 Weights

100.0 GB

FP8 Weights

50.0 GB

INT4 Weights

25.0 GB

KV-Cache per Token81920 bytes
Activation Estimate2.00 GB

Fits on (single-node)

B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM FP8H100 PCIe FP8H100 NVL FP8

GPU Recommendations

B200 SXMoptimal

BF16 · 1 GPU · tensorrt-llm

100/100

score

Throughput

560.0 tok/s

Cost/Month

$4261

Cost/M Tokens

$2.90

Use this config →
B100 SXMoptimal

BF16 · 1 GPU · tensorrt-llm

100/100

score

Throughput

560.0 tok/s

Cost/Month

$4271

Cost/M Tokens

$2.90

Use this config →
GB200 NVL72 (per GPU)optimal

BF16 · 1 GPU · tensorrt-llm

100/100

score

Throughput

560.0 tok/s

Cost/Month

$6169

Cost/M Tokens

$4.19

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
google$0.07$0.30
Cheapest

Quality Benchmarks

MMLU
78.9
HumanEval
52.0
GSM8K
82.0
MT-Bench
80.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

Supported Precisions

BF16 (default)

Similar Models