# Holo4 27B

> H Company's 27B dense computer-use model, released September 28, 2026: one vision-language model that clicks, writes code and calls MCP or API tools, scoring 85.2% on OSWorld at $0.08 per task.

- Maker: H Company
- Line: Holo
- Canonical page: https://ai-tldr.dev/models/holo4-27b/
- Updated: 2026-10-06

## In short

Holo4 27B is H Company's 27B dense computer-use model, released September 28, 2026: one vision-language model that clicks, writes code and calls MCP or API tools, scoring 85.2% on OSWorld at $0.08 per task. It costs $0.40 per million input tokens and $3.00 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 | $0.40 / 1M tokens (cached $0.04) | [2] |
| Output price | $3.00 / 1M tokens | [2] |
| Licence | CC-BY-NC-4.0 · open weights | [1] |
| Released | 28 September 2026 | [3] |
| Parameters | 27B (dense) | [1] |

## Sources

1. [Hcompany/Holo4-27B model card on Hugging Face](https://huggingface.co/Hcompany/Holo4-27B)
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 27B is a vision-language model for computer use from H Company, the Paris-founded AI research lab, released on September 28, 2026 together with the smaller Holo4 35B-A3B. It is the larger of the two Holo4 sizes, a 27B dense model built on Qwen3.8-27B, and H Company positions it for the best accuracy on long, multi-step tasks across web, desktop and mobile. Its weights are on Hugging Face under the non-commercial CC BY-NC 4.0 license, and it is served on H Company's OpenAI-compatible H Models API as holo4-27b.

The model 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, all through the same call. H Company says it runs on desktops, on the web, on Android, in a code sandbox and against business APIs, without picking a different model per platform. With H Company's hai-agents harness, screenshots and tool results go to the model and the harness executes the clicks, typing, code and tool calls it requests.

On H Company's launch table Holo4 27B scores 85.2% on OSWorld at $0.08 per task, 61.7% average partial score on the long workflows of OSWorld 2.0 (41.5% success, $1.22 per task), 85.1% on AndroidWorld, 45.4% on the 600 public AutomationBench tasks and 44.1% on ALE-CLI. In each case it improves on its Qwen3.8 27B base model. H Company says Holo4 trails only the strongest closed models on long workflows: on OSWorld 2.0, Opus 5.5 scores 81.8% at $8.48 per task. H Company publishes every trajectory behind its public benchmark scores.

Training started with 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%) and mobile (3%), with the rest covering multimodal reasoning, GUI grounding and text-only tool use and coding. Asynchronous online reinforcement learning on long-horizon tasks then trained two LoRA experts, one for desktop and web and one for terminal, MCP and API, which were merged back into the fine-tuned model with equal weight and no further training.

Weights come in BF16, FP8, NVFP4 and Q4 GGUF builds, and the config sets a maximum context of 262,144 tokens. On the H Models API, Holo4 27B costs $0.40 per million input tokens ($0.04 cached) and $3.00 per million output tokens.

## Benchmarks

- Agentic Task Factory — MCP (14 tool servers): 89.4% ([source](https://hcompany.ai/newsroom/holo4))
- OSWorld: 85.2% ([source](https://hcompany.ai/newsroom/holo4))
- AndroidWorld: 85.1% ([source](https://hcompany.ai/newsroom/holo4))
- Agentic Task Factory — Web (47 web apps): 80.2% ([source](https://hcompany.ai/newsroom/holo4))
- Agentic Task Factory — Desktop (17 desktop apps): 72% ([source](https://hcompany.ai/newsroom/holo4))
- OSWorld 2.0 (average partial score): 61.7% ([source](https://hcompany.ai/newsroom/holo4))
- AutomationBench (600 public tasks): 45.4% ([source](https://hcompany.ai/newsroom/holo4))
- ALE-CLI (105-task Linux split): 44.1% ([source](https://hcompany.ai/newsroom/holo4))

## Pricing

- Input: $0.40 / 1M tokens
- Cached input: $0.04 / 1M tokens
- Output: $3.00 / 1M tokens

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

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

## Strengths

- One model for GUI actions, code execution and MCP or API tool calls, on desktop, web and Android
- 85.2% on OSWorld at $0.08 per task and 85.1% on AndroidWorld in H Company's launch table
- 61.7% average partial score on OSWorld 2.0 long workflows at $1.22 per task
- Improves on its Qwen3.8 27B base across every benchmark H Company reported
- Open weights in BF16, FP8, NVFP4 and Q4 GGUF, plus a hosted OpenAI-compatible API
- 262,144-token context for agent runs of hundreds of steps

## Best for

- Reach for it for computer-use agents that operate desktop software, websites and Android apps through screenshots and clicks.
- Reach for it for business workflows that mix GUI steps with MCP servers, APIs and code in the same run.
- Reach for it for research and evaluation of open computer-use agents, using the published trajectories.
- Look elsewhere for commercial self-hosting: the 27B weights are CC BY-NC 4.0 (non-commercial); Holo4 35B-A3B is Apache 2.0, or use the H Models API.

## How to access

- [H Models API](https://hub.hcompany.ai/models-api/introduction) — model id `holo4-27b`
- [Hugging Face (weights)](https://huggingface.co/Hcompany/Holo4-27B) — model id `Hcompany/Holo4-27B`

## FAQ

### What is Holo4 27B?

Holo4 27B is a 27B dense vision-language model for computer use from H Company, released on September 28, 2026. Built on Qwen3.8-27B, it clicks and types on screens, writes and runs code, and calls MCP or API tools across desktop, web and Android.

### Is Holo4 27B open source?

Its weights are open on Hugging Face (BF16, FP8, NVFP4 and Q4 GGUF) under the CC BY-NC 4.0 license, which is non-commercial. The smaller Holo4 35B-A3B is released under Apache 2.0.

### How well does Holo4 27B score on OSWorld?

H Company reports 85.2% on OSWorld at $0.08 per task, against 84.3% for its Qwen3.8 27B base, and 61.7% average partial score on OSWorld 2.0 at $1.22 per task, against 48.0% for Qwen3.8 27B and 81.8% for Opus 5.5.

### How much does Holo4 27B cost on the H Models API?

$0.40 per million input tokens, $0.04 per million cached input tokens and $3.00 per million output tokens. The model ID is holo4-27b.

### What is the context window of Holo4 27B?

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

### How does Holo4 27B differ from Holo4 35B-A3B?

Holo4 27B is dense and scores higher (85.2% against 80.8% on OSWorld, 61.7% against 30.9% on OSWorld 2.0). Holo4 35B-A3B is a Mixture-of-Experts model with 3B active parameters that H Company describes as close to 27B accuracy, cheaper and faster, and it is Apache 2.0 licensed.

## Links

- [H Company — Holo4: powering generalist computer-use agents](https://hcompany.ai/newsroom/holo4)
- [Hcompany/Holo4-27B model card on Hugging Face](https://huggingface.co/Hcompany/Holo4-27B)
- [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/holo4-27b/
