Skip to content
Local AI Wizard
Your machine
Theme

Eagle2.5-8B

nvidia · nvidia/Eagle2.5-8B

Weights license: Publisher terms: CC BY-NC 4.0 or NVIDIA License (Eagle 2.5) · code and components may use other terms

Reported by the publisher34 resultsnvidia's model card · read 2026-10-25 · not ranked · see them
Memory needed~7 GBQ4 weights + working room, before the machine's reserve
Parameters8.1 BHub safetensors total
Repository updated2025-11-29A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

34 results · nvidia's model card · read 2026-10-25
MVBench test
74.8Video Benchmarks
Perception_test val
82.0Video Benchmarks
EgoSchema fullset
72.2Video Benchmarks
MMB-Video
1.94Video Benchmarks
MLVU val
77.6Video Benchmarks
LVBench val
66.4Video Benchmarks
Video-MME w/o subtitle
72.4Video Benchmarks
Video-MME w subtitle
75.7Video Benchmarks
Every reported result34
CG-Bench Clue
55.8Video Benchmarks
CG-Bench Long
46.6Video Benchmarks
CG-Bench mIoU
13.4Video Benchmarks
HourVideo Dev
44.5Video Benchmarks
HourVideo Test
41.8Video Benchmarks
Charade-STA mIoU
65.9Video Benchmarks
HD-EPIC
42.9Video Benchmarks
HRVideoBench
68.5Video Benchmarks
EgoPlan val
45.3Video Benchmarks
OpenEQA
63.5Embodied Benchmarks
ERQA
38.3Embodied Benchmarks
EgoPlan val
45.3Embodied Benchmarks
DocVQA test
94.1Image Benchmarks
ChartQA test
87.5Image Benchmarks
InfoVQA test
80.4Image Benchmarks
TextVQA val
83.7Image Benchmarks
OCRBench test
869Image Benchmarks
MMstar test
66.2Image Benchmarks
RWQA test
76.7Image Benchmarks
AI2D test
84.5Image Benchmarks
MMMU val
55.8Image Benchmarks
MMBench_V11 test
81.7Image Benchmarks
MMVet GPT-4-Turbo
62.9Image Benchmarks
HallBench avg
54.7Image Benchmarks
MathVista testmini
67.8Image Benchmarks
Avg Score
75.6Image Benchmarks

Values as printed on the card, with the publisher's own settings (card section: Video Benchmarks; Embodied Benchmarks); column “Eagle2.5-8B”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 90

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 90

Within memory, outside the fast part 26

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 26

One memory tier short 3

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

The model card could not be read (missing or gated)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
nvidia/Eagle2.5-8B
Task
image-text-to-text
Architecture
Eagle2_5_VLForConditionalGeneration
Library in source
transformers
Weight license
Publisher terms: CC BY-NC 4.0 or NVIDIA License (Eagle 2.5)NVlabs/Eagle README, License/Terms of Use: pretrained weights under either CC BY-NC 4.0 or the NVIDIA License (Eagle2_5/LICENSE_MODEL), non-commercial use only · read 2026-10-18source
Commercial use
Not allowed NVlabs/Eagle Eagle2_5/LICENSE_MODEL (NVIDIA License, Section 3.3; the alternative is CC BY-NC 4.0) · read 2026-10-18license text
Languages
MultilingualModel card metadata · read 2026-10-25source
Every stored field14 fields
Revision checked
61e45235a1e4a35222b86383479b3b004f4809d7
Architecture
Eagle2_5_VLForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Declared base models
Qwen/Qwen2.5-7B-Instruct · google/siglip2-so400m-patch16-512
Formats
transformers, safetensors
Access
Gated (auto)
Publisher kind
Official
Hub parameter count
8,070,777,280safetensors.total
Repository created
2025-04-12creation is not the model's release
Repository updated
2025-11-29a commit is not a release date
Hub downloads (30 days) · likes
14,678 · 51this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tagsHub overview and file listing · read 2026-10-19
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.