# Holo4 35B-A3B

> H Company's Apache-2.0 Mixture-of-Experts computer-use model, 35B total and 3B active parameters, released September 28, 2026: clicks, codes and calls tools, scoring 80.8% on OSWorld at $0.05 per task.

- Maker: H Company
- Line: Holo
- Canonical page: https://ai-tldr.dev/models/holo4-35b-a3b/
- Updated: 2026-10-06

## In short

Holo4 35B-A3B is H Company's Apache-2.0 Mixture-of-Experts computer-use model, 35B total and 3B active parameters, released September 28, 2026: clicks, codes and calls tools, scoring 80.8% on OSWorld at $0.05 per task. It costs $0.30 per million input tokens and $2.00 per million output tokens. You can use it through H Models API and Hugging Face (weights).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 262,144 tokens (256K) | [1] |
| Input price | $0.30 / 1M tokens (cached $0.03) | [2] |
| Output price | $2.00 / 1M tokens | [2] |
| Licence | Apache-2.0 · open weights | [1] |
| Released | 28 September 2026 | [3] |
| Parameters | 35B total · 3B active | [1] |

## Sources

1. [Hcompany/Holo4-35B-A3B model card on Hugging Face](https://huggingface.co/Hcompany/Holo4-35B-A3B)
2. [H Company — Holo4: powering generalist computer-use agents](https://hcompany.ai/newsroom/holo4)
3. [hai-agents harness on GitHub](https://github.com/hcompai/hai-agents-python)

## Overview

Holo4 35B-A3B is a Mixture-of-Experts vision-language model for computer use from H Company, the Paris-founded AI research lab, released on September 28, 2026 alongside the larger Holo4 27B. It has 35B total parameters with 3B active, is built on Qwen3.6-35B-A3B, and H Company describes it as close to 27B accuracy, cheaper and faster. Its weights are on Hugging Face under Apache 2.0, and it is served on H Company's OpenAI-compatible H Models API as holo4-35b-a3b, the model the API docs suggest starting with because its latency suits interactive loops.

Like Holo4 27B, it works through whatever interface a task needs: it clicks and types on a screen, writes and runs its own code, and calls MCP or API tools, with the same call for desktop, web, Android, a code sandbox or business APIs. With H Company's hai-agents harness, screenshots and tool results go to the model and the harness executes the actions it requests.

On H Company's launch table Holo4 35B-A3B scores 80.8% on OSWorld at $0.05 per task, 77.6% on AndroidWorld at $0.07, 34.5% on the 600 public AutomationBench tasks at $0.02, and 30.9% average partial score on OSWorld 2.0 at $0.61 per task. On H Company's held-out Agentic Task Factory sets it reaches 85.4% on MCP tool servers, 70.8% on web apps and 64.8% on desktop apps. On the 120 held-out AutomationBench tasks it scores 31.7%, against 13.1% for its Qwen3.6 35B-A3B base.

Training followed the Holo4 recipe: supervised fine-tuning on 127B tokens, about three quarters of them successful agentic trajectories from H Company's Agentic Task Factory (desktop 45%, web 14%, MCP and API 12%, mobile 3%), then asynchronous online reinforcement learning that trained two LoRA experts, one for desktop and web and one for terminal, MCP and API, merged back into the fine-tuned model with equal weight.

Weights come in BF16, FP8, NVFP4 and Q4 GGUF builds, with a 262,144-token maximum context in the config. On the H Models API it costs $0.30 per million input tokens ($0.03 cached) and $2.00 per million output tokens.

## Benchmarks

- Agentic Task Factory — MCP (14 tool servers): 85.4% ([source](https://hcompany.ai/newsroom/holo4))
- OSWorld: 80.8% ([source](https://hcompany.ai/newsroom/holo4))
- AndroidWorld: 77.6% ([source](https://hcompany.ai/newsroom/holo4))
- Agentic Task Factory — Web (47 web apps): 70.8% ([source](https://hcompany.ai/newsroom/holo4))
- Agentic Task Factory — Desktop (17 desktop apps): 64.8% ([source](https://hcompany.ai/newsroom/holo4))
- AutomationBench (600 public tasks): 34.5% ([source](https://hcompany.ai/newsroom/holo4))
- OSWorld 2.0 (average partial score): 30.9% ([source](https://hcompany.ai/newsroom/holo4))
- ALE-CLI (105-task Linux split): 30.9% ([source](https://hcompany.ai/newsroom/holo4))

## Pricing

- Input: $0.30 / 1M tokens
- Cached input: $0.03 / 1M tokens
- Output: $2.00 / 1M tokens

H Models API rates as listed in H Company's Holo4 launch post.

Source: https://hcompany.ai/newsroom/holo4

## Strengths

- Apache 2.0 open weights, usable commercially, in BF16, FP8, NVFP4 and Q4 GGUF
- Only 3B of 35B parameters active per token, aimed at lower cost and latency than Holo4 27B
- 80.8% on OSWorld at $0.05 per task and 77.6% on AndroidWorld in H Company's launch table
- 85.4% on the MCP tool-server set of H Company's held-out Agentic Task Factory
- One model for GUI actions, code execution and MCP or API tool calls
- 262,144-token context and an OpenAI-compatible hosted API

## Best for

- Reach for it for interactive computer-use agents where latency and cost per task matter more than peak accuracy.
- Reach for it for self-hosted, commercial agent products that need an Apache-2.0 computer-use model.
- Reach for it for workflows that combine MCP servers and APIs with GUI steps on desktop, web or Android.
- Look elsewhere for the longest multi-step desktop workflows: Holo4 27B scores 61.7% against 30.9% on OSWorld 2.0.

## How to access

- [H Models API](https://hub.hcompany.ai/models-api/introduction) — model id `holo4-35b-a3b`
- [Hugging Face (weights)](https://huggingface.co/Hcompany/Holo4-35B-A3B) — model id `Hcompany/Holo4-35B-A3B`

## FAQ

### What is Holo4 35B-A3B?

Holo4 35B-A3B is a Mixture-of-Experts vision-language model for computer use from H Company, released on September 28, 2026, with 35B total and 3B active parameters. Built on Qwen3.6-35B-A3B, it clicks and types on screens, writes and runs code, and calls MCP or API tools.

### What license is Holo4 35B-A3B under?

Apache 2.0. Its base model, Qwen3.6-35B-A3B, is also Apache 2.0. The larger Holo4 27B is CC BY-NC 4.0 (non-commercial).

### How well does Holo4 35B-A3B score?

In H Company's launch table it scores 80.8% on OSWorld at $0.05 per task, 77.6% on AndroidWorld, 34.5% on AutomationBench's public tasks, 30.9% on OSWorld 2.0 and 30.9% on ALE-CLI.

### How much does Holo4 35B-A3B cost on the H Models API?

$0.30 per million input tokens, $0.03 per million cached input tokens and $2.00 per million output tokens. The model ID is holo4-35b-a3b.

### What is the context window of Holo4 35B-A3B?

H Company lists a 256K context; the model card gives a maximum context length of 262,144 tokens in the config.

### Should I use Holo4 35B-A3B or Holo4 27B?

H Company's API docs suggest starting with holo4-35b-a3b for its latency in interactive loops and moving to holo4-27b for complex multi-step tasks and novel environments. Holo4 27B scores higher on every benchmark in the launch table, most of all on OSWorld 2.0 (61.7% against 30.9%).

## Links

- [H Company — Holo4: powering generalist computer-use agents](https://hcompany.ai/newsroom/holo4)
- [Hcompany/Holo4-35B-A3B model card on Hugging Face](https://huggingface.co/Hcompany/Holo4-35B-A3B)
- [H Models API — introduction and model IDs](https://hub.hcompany.ai/models-api/introduction)
- [Holo4 agent trajectories](https://trajectories.hcompany.ai/)
- [hai-agents harness on GitHub](https://github.com/hcompai/hai-agents-python)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/holo4-35b-a3b/
