LLM Reference

Holo2-235B-A22B

Released
2025-11-13
Last refreshed
2026-06-07
Status
Researched today
Open WeightsNon-commercial onlyMultimodalAgentsLong contextVisionAgentsVision

Holo2-235B-A22B has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating agents, long context, and vision
  • Workloads that can use a 262k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Strict JSON or tool-calling flows
  • Teams that need a tracked hosted API route today
Specifications
Family
Holo
Released
2025-11-13
Context
262k
Parameters
236
Architecture
moe
Specialization
computer-use
Openness
Open weights
License
CC-BY-NC-4.0Non-commercial only
Training
supervised-finetuning
Created by

Agentic AI for Action

Paris, France
Founded 2023
Website
Pricing

No tracked provider token pricing is available yet.

About

Holo2-235B-A22B is H Company's 236B (22B active) sparse MoE computer-use VLM under CC-BY-NC-4.0, fine-tuned from Qwen3-VL-235B-A22B-Thinking. Achieves SOTA 84.28% average UI localization across six benchmarks and 78.5% on ScreenSpot-Pro with 3-step agentic localization. Commercial use requires contacting H Company.

Holo2-235B-A22B is H Company's 236B (22B active) sparse MoE computer-use VLM under CC-BY-NC-4.0, fine-tuned from Qwen3-VL-235B-A22B-Thinking. Achieves SOTA 84.28% average UI localization across six benchmarks and 78.5% on ScreenSpot-Pro with 3-step agentic localization. Commercial use requires contacting H Company.

Holo2-235B-A22B has a 262k-token context window.

Top use-case fit: coding, agents, and build tasks

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

VisionMultimodal

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
ScreenSpot-Pro70.6ScreenSpot-Pro - single-step UI localizationhttps://huggingface.co/Hcompany/Holo2-235B-A22B
ScreenSpot-Pro78.5ScreenSpot-Pro - agentic localization (3 steps)https://huggingface.co/Hcompany/Holo2-235B-A22B
OSWorld-G79.0OSWorld-G - UI groundinghttps://huggingface.co/Hcompany/Holo2-235B-A22B
WebClick94.3WebClick-v1 - UI localizationhttps://huggingface.co/Hcompany/Holo2-235B-A22B
ScreenSpot-v295.9ScreenSpot-v2 - UI localizationhttps://huggingface.co/Hcompany/Holo2-235B-A22B

Migration checks

No linked migration route is available for this model yet.