Skip to content
Updated minutes ago
AI21

Jamba Instruct

AI21 · moe · 52B parameters · 256,000 context

Quality
66.0

Architecture Details

TypeMOE
Total Parameters52B
Active Parameters12B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size65,536
Total Experts16
Active Experts2

Memory Requirements

BF16 Weights

104.0 GB

FP8 Weights

52.0 GB

INT4 Weights

26.0 GB

KV-Cache per Token65536 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
ai21$0.50$0.70
Cheapest

Quality Benchmarks

MMLU
72.0
HumanEval
42.0
GSM8K
68.0
MT-Bench
75.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

Supported Precisions

BF16 (default)

Similar Models