Marketplace · Text & chat

moondream:1.8b

Call moondream:1.8b through one OpenAI-compatible API. It's served by 2 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.045
per 1M output tokens
£1 buys about 22 million tokens (≈ 17 million words)
Hosts
2
Loaded now
0

At a glance.

vision

  • Type: Text & chat
  • Hosts serving it now: 2 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 2,048 tokens
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="moondream:1.8b",
    messages=[{"role": "user", "content": "Hello"}],
)

moondream:1.8b in detail.

moondream2 is a small vision language model designed to run efficiently on edge devices.

Published by
vikhyatk
Parameters
1.9B
Download size
1.7 GB (as packaged for Ollama)
Quantisation
Q4_0
Format
gguf
Architecture
moondream1
Licence
Apache 2.0
Task
image text to text
Library
transformers
First published
4 Mar 2024
Last updated
23 Sep 2026
Downloads (30 days)
2.3 million on Hugging Face
Likes
1,450

moondream1 text-generation image-text-to-text

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

⚠️ This repository contains the latest version of Moondream 2, our previous generation model. The latest version of Moondream is Moondream 3 (Preview).

---

Moondream is a small vision language model designed to run efficiently everywhere.

Website / Demo / GitHub

This repository contains the latest (2025-06-21) release of Moondream 2, as well as historical releases. The model is updated frequently, so we recommend specifying a revision as shown below if you're using it in a production application.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image

model = AutoModelForCausalLM.from_pretrained(
    "vikhyatk/moondream2",
    revision="2025-06-21",
    trust_remote_code=True,
    device_map={"": "cuda"}  # ...or 'mps', on Apple Silicon
)

### Captioning
print("Short caption:")
print(model.caption(image, length="short")["caption"])

print("\nNormal caption:")
for t in model.caption(image, length="normal", stream=True)["caption"]:
    # Streaming generation example, supported for caption() and detect()
    print(t, end="", flush=True)
print(model.caption(image, length="normal"))

### Visual Querying
print("\nVisual query: 'How many people are in the image?'")
print(model.query(image, "How many people are in the image?")["answer"])

### Object Detection
print("\nObject detection: 'face'")
objects = model.detect(image, "face")["objects"]
print(f"Found {len(objects)} face(s)")

### Pointing
print("\nPointing: 'person'")
points = model.point(image, "person")["points"]
print(f"Found {len(points)} person(s)")

Changelog

2025-06-21 (full release notes)

  • Grounded Reasoning

Introduces a new step-by-step reasoning mode that explicitly grounds reasoning in spatial positions within the image before answering, leading to more precise visual interpretation (e.g., chart median calculations, accurate counting). Enable with reasoning=True in the query skill to trade off speed vs. accuracy.

  • Sharper Object Detection

Uses reinforcement learning on higher-quality bounding-box annotations to reduce object clumping and improve fine-grained detections (e.g., distinguishing “blue bottle” vs. “bottle”).

  • Faster Text Generation

Yields 20–40 % faster response generation via a new “superword” tokenizer and lightweight tokenizer transfer hypernetwork, which reduces the number of tokens emitted without loss in accuracy and eases future multilingual extensions.

  • Improved UI Understanding

Boosts ScreenSpot (UI element localization) performance from an F1\@0.5 of 60.3 to 80.4, making Moondream more effective for UI-focused applications.

  • Reinforcement Learning Enhancements

RL fine-tuning applied across 55 vision-language tasks to reinforce grounded reasoning and detection capabilities, with a roadmap to expand to \~120 tasks in the next update.

2025-04-15 (full release notes)

  1. Improved chart understanding (ChartQA up from 74.8 to 77.5, 82.2 with PoT)
  2. Added temperature and nucleus sampling to reduce repetitive outputs
  3. Better OCR for documents and tables (prompt with “Transcribe the text” or “Transcribe the text in natural reading order”)
  4. Object detection supports document layout detection (figure, formula, text, etc)
  5. UI understanding (ScreenSpot F1\@0.5 up from 53.3 to 60.3)
  6. Improved text understanding (DocVQA up from 76.5 to 79.3, TextVQA up from 74.6 to 76.3)

2025-03-27 (full release notes)

  1. Added support for long-form captioning
  2. Open vocabulary image tagging
  3. Improved counting accuracy (e.g. CountBenchQA increased from 80 to 86.4)
  4. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
  5. Improved object detection, especially for small objects (e.g. COCO up from 30.5 to 51.2)
  6. Fixed token streaming bug affecting multi-byte unicode characters
  7. gpt-fast style compile() now supported in HF Transformers implementation

Sources: vikhyatk/moondream2 on Hugging Face · moondream:1.8b on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving moondream:1.8b right now
HostTierPriceMeasured speedHealthStateRent
Lumaram-MacMini-M4-001L1£0.018 in · £0.045 out106 tok/s · 11 ms first token81loads on request—
GTX 1080 Ti (11G)L1£0.029 in · £0.072 out21 tok/s · 56 ms first token78loads on request£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

2 machines serve moondream:1.8b today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
2
0 loaded in memory
Price to beat
£0.045
per 1M output tokens
Fastest measured
106 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load moondream:1.8b, and the platform benchmarks it on your hardware before your first request.