Skip to content
Updated minutes ago
NVIDIA

Eagle 2 1B

NVIDIA · dense · 1.3B parameters · 4,096 context

Quality
65.0

Parameters

1.3B

Context Window

4K tokens

Architecture

Dense

Best GPU

RTX 4070 Ti

Intelligence Brief

Eagle 2 1B is a 1.3B parameter DENSE model from NVIDIA, featuring Multi-Head Attention (MHA) with 24 layers and 2,048 hidden dimensions. With a 4,096 token context window, it supports vision. For self-hosted inference, RTX 4070 Ti delivers optimal throughput at $237/month.

Architecture Details

TypeDENSE
Total Parameters1.3B
Active Parameters1.3B
Layers24
Hidden Dimension2,048
Attention Heads16
KV Heads16
Head Dimension128
Vocab Size151,936

Memory Requirements

BF16 Weights

2.6 GB

FP8 Weights

1.3 GB

INT4 Weights

0.7 GB

KV-Cache per Token196608 bytes
Activation Estimate0.20 GB

GPU Compatibility Matrix

Eagle 2 1B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
B300288GB
B100 SXM192GB
GB200 NVL72 (per GPU)192GB
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
H200 SXM141GB
H2096GB
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
L4048GB
RTX 6000 Ada48GB
L2048GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
A1664GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

RTX 4070 Tioptimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

1.0K tok/s

Latency (ITL)

1.0ms

Est. TTFT

0ms

Cost/Month

$237

Cost/M Tokens

$0.09

Use this config →
RTX 3080optimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

1.6K tok/s

Latency (ITL)

0.6ms

Est. TTFT

0ms

Cost/Month

$133

Cost/M Tokens

$0.03

Use this config →
RTX 4060optimal

BF16 · 1 GPU · vllm

90/100

score

Throughput

564.9 tok/s

Latency (ITL)

1.8ms

Est. TTFT

0ms

Cost/Month

$209

Cost/M Tokens

$0.14

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

RTX 4070 Ti

$237/mo

Min VRAM: 1 GB

Scale

Multi-GPU

RTX 4070 Ti

1.0K tok/s

Best available config

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

RTX 4070 Ti
1.0K tok/s
RTX 3080
1.6K tok/s
RTX 4060
564.9 tok/s

VRAM Breakdown (RTX 4070 Ti, BF16)

Weights
KV
Act
Weights 2.6 GBKV-Cache 3.2 GBActivations 1.6 GBOverhead 0.2 GB

Precision Impact

bf16

2.6 GB

weights/GPU

~1.0K tok/s

fp8

1.3 GB

weights/GPU

int4

0.7 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Eagle 2 1B

Similar Models

Lower qualityCompare →

Llama 3.2 1B

1.24B params · dense

Quality: 38

from $0.03/M

Larger context, Lower qualityCompare →
Lower qualityCompare →
Larger context, Lower qualityCompare →

Frequently Asked Questions

How much VRAM does Eagle 2 1B need for inference?

Eagle 2 1B requires approximately 2.6 GB of VRAM at BF16 precision, 1.3 GB at FP8, or 0.7 GB at INT4 quantization. Additional VRAM is needed for KV-cache (196608 bytes per token) and activations (~0.20 GB).

What is the best GPU for Eagle 2 1B?

The top recommended GPU for Eagle 2 1B is the RTX 4070 Ti using BF16 precision. It achieves approximately 1.0K tokens/sec at an estimated cost of $237/month ($0.09/M tokens). Score: 90/100.

How much does Eagle 2 1B inference cost?

Eagle 2 1B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.