Updated minutes ago
NVIDIA

Eagle 2.5 8B

NVIDIA · dense · 8B parameters · 16,384 context

Quality
65.0
Calculate ROI →Compare with othersFine-Tune This Model →

Parameters

8B

Context Window

16K tokens

Architecture

Dense

Best GPU

A30

Intelligence Brief

Eagle 2.5 8B is a 8B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 16,384 token context window, it supports vision, code. For self-hosted inference, A30 delivers optimal throughput at $332/month.

Architecture Details

TypeDENSE
Total Parameters8B
Active Parameters8B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size152,064

Memory Requirements

BF16 Weights

16.0 GB

FP8 Weights

8.0 GB

INT4 Weights

4.0 GB

KV-Cache per Token131072 bytes
Activation Estimate0.50 GB

Fits on (single GPU) — most practical first

BEST FITRTX 40608GBINT4RTX 30708GBINT4RTX 308010GBFP8RTX 4070 Ti12GBFP8RTX 4070 Super12GBFP8RTX 306012GBFP8A400016GBFP8RTX 408016GBFP8T416GBFP8V100 16GB16GBFP8RTX 4060 Ti 16GB16GBFP8A216GBFP8

GPU Compatibility Matrix

Eagle 2.5 8B is compatible with 90% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
96%
98%
99%
B300288GB
94%
97%
99%
B100 SXM192GB
92%
96%
98%
GB200 NVL72 (per GPU)192GB
92%
96%
98%
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
91%
96%
98%
H200 SXM141GB
89%
94%
97%
H2096GB
83%
92%
96%
GH20096GB
83%
92%
96%
Ada Lovelace(11 GPUs)
L40S48GB
67%
83%
92%
L4048GB
67%
83%
92%
RTX 6000 Ada48GB
67%
83%
92%
L2048GB
67%
83%
92%
Ampere(16 GPUs)
A100 80GB SXM80GB
80%
90%
95%
A100 80GB PCIe80GB
80%
90%
95%
A1664GB
75%
88%
94%
RTX A600048GB
67%
83%
92%
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

314.9 tok/s

Latency (ITL)

3.2ms

Est. TTFT

1ms

Cost/Month

$332

Cost/M Tokens

$0.40

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

340.2 tok/s

Latency (ITL)

2.9ms

Est. TTFT

1ms

Cost/Month

$370

Cost/M Tokens

$0.41

Use this config →
RTX 3090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

315.9 tok/s

Latency (ITL)

3.2ms

Est. TTFT

1ms

Cost/Month

$180

Cost/M Tokens

$0.22

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

A30

$332/mo

Min VRAM: 8 GB

Scale

Multi-GPU

RTX 3060 x2

190.4 tok/s

TP· $114/mo

Open Full Calculator →

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

A30
314.9 tok/s
RTX 4090
340.2 tok/s
RTX 3090
315.9 tok/s

VRAM Breakdown (A30, BF16)

Weights
Act
Weights 16.0 GBKV-Cache 2.1 GBActivations 4.0 GBOverhead 1.3 GB

Precision Impact

bf16

16.0 GB

weights/GPU

~314.9 tok/s

fp8

8.0 GB

weights/GPU

int4

4.0 GB

weights/GPU

Capabilities

Features

✗ Tool Use✓ Vision✓ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output

Supported Frameworks

vllmtensorrt-llm

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Eagle 2.5 8B

Similar Models

Eagle 2 9B

9B params · dense

Quality: 65

Similar specsCompare →

Aya 23 8B

8B params · dense

Quality: 50

from $0.60/M

Lower qualityCompare →

DeepSeek R1 Distill 8B

8B params · dense

Quality: 88

from $0.20/M

Larger context, Higher qualityCompare →

Llama 3 8B

8B params · dense

Quality: 63

from $0.20/M

Similar specsCompare →

Llama Guard 3 8B

8B params · dense

Quality: 50

from $0.20/M

Larger context, Lower qualityCompare →

Frequently Asked Questions

How much VRAM does Eagle 2.5 8B need for inference?

Eagle 2.5 8B requires approximately 16.0 GB of VRAM at BF16 precision, 8.0 GB at FP8, or 4.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~0.50 GB).

What is the best GPU for Eagle 2.5 8B?

The top recommended GPU for Eagle 2.5 8B is the A30 using BF16 precision. It achieves approximately 314.9 tokens/sec at an estimated cost of $332/month ($0.40/M tokens). Score: 100/100.

How much does Eagle 2.5 8B inference cost?

Eagle 2.5 8B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.