Skip to content

Holo3 35B A3B

H Company · Holo · measured on live video

Overshoot API id Hcompany/Holo3-35B-A3B

Compare this model

Real-time under 200 msOpen weightsImage

Intelligence
74
Speed
423 tok/s
TTFT
35 ms
E2E
92 ms
Blended $/1M
$0.12
Params
35B
Context
128k
License
Apache-2.0
Released
Apr 2026

Speed, TTFT, E2E, and price at Overshoot, US East (Virginia) reference region. Rank is position on the VLM Intelligence Index.

Capability breakdown

OCR & Text82%Document & Chart79%Scene & Spatial73%Video QA60%Grounding72%Struct. Extraction75%

Intelligence over time

647178Apr 2026Jun 2026

Provider & region options

Fastest loop: Overshoot · US East (Virginia) · 92 ms end to end.

OvershootUS East (Virginia)423 tok/s35 ms92 ms$0.12<200 ms
OvershootUS West (Oregon)423 tok/s45 ms102 ms$0.12<200 ms
OvershootEU West (Ireland)423 tok/s51 ms107 ms$0.12<200 ms
OvershootEU Central (Frankfurt)423 tok/s56 ms113 ms$0.12<200 ms
OvershootAsia Pacific (Tokyo)423 tok/s73 ms130 ms$0.12<200 ms
FireworksUS East (Virginia)299 tok/s51 ms131 ms$0.12<200 ms
OvershootAsia Pacific (Mumbai)423 tok/s81 ms138 ms$0.12<200 ms
OvershootMiddle East (Dubai)423 tok/s84 ms141 ms$0.12<200 ms
FireworksUS West (Oregon)299 tok/s62 ms142 ms$0.12<200 ms
OvershootSouth America (São Paulo)423 tok/s93 ms149 ms$0.12<200 ms
TogetherUS East (Virginia)262 tok/s58 ms150 ms$0.12<200 ms
FireworksEU West (Ireland)299 tok/s74 ms154 ms$0.12<200 ms
TogetherUS West (Oregon)262 tok/s73 ms164 ms$0.12<200 ms
TogetherEU West (Ireland)262 tok/s74 ms166 ms$0.12<200 ms
vLLM (self-host)US East (Virginia)212 tok/s74 ms188 ms$0.08<200 ms
vLLM (self-host)EU West (Ireland)212 tok/s83 ms197 ms$0.08<200 ms

Sample outputs

Illustrative samples shared across models, not verbatim output from Holo3 35B A3B.

Scene description

Describe what's happening in this camera frame.

A forklift is reversing toward loading bay 3 while a worker in a hi-vis vest signals from the left. Two pallets remain unwrapped near the dock edge.

OCR + extraction

Read the shipping label and return structured JSON.

{ "tracking": "1Z A24 9W7 03 8421 990 4", "carrier": "UPS", "weight_kg": 12.4, "dest": "Portland, OR 97204" }

Grounding

Point to every person not wearing a hard hat.

2 detections, [x:0.41, y:0.62, w:0.08, h:0.19] conf 0.94 · [x:0.77, y:0.55, w:0.07, h:0.21] conf 0.88.

Where it ranks