Skip to content
Updated minutes ago
NVIDIA

Parakeet CTC 0.6B

NVIDIA · dense · 0.6B parameters · 4,096 context

Quality
50.0

Architecture Details

TypeDENSE
Total Parameters0.6B
Active Parameters0.6B
Layers18
Hidden Dimension768
Attention Heads8
KV Heads8
Head Dimension96
Vocab Size128,000

Memory Requirements

BF16 Weights

1.2 GB

FP8 Weights

0.6 GB

INT4 Weights

0.3 GB

KV-Cache per Token6912 bytes
Activation Estimate0.10 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

B200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Cost/Month

$4261

Cost/M Tokens

$0.46

Use this config →
B100 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Cost/Month

$4271

Cost/M Tokens

$0.46

Use this config →
GB200 NVL72 (per GPU)optimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Cost/Month

$6169

Cost/M Tokens

$0.67

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
nvidia-nim$0.03$0.03
Cheapest

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

tensorrt-llmvllm

Supported Precisions

BF16 (default)FP8INT4

Similar Models