Marketplace · Decision (classify · yes/no · score)
d1:3b
Call d1:3b through one OpenAI-compatible API. It's served by 1 host 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.
At a glance.
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
# /v1/systemone (decision models are not in the OpenAI SDK)
r = requests.post("https://inpherio.co.uk/v1/systemone", headers={"Authorization": "Bearer KEY"},
json={"model": "d1:3b", "state": "My order arrived broken.",
"questions": {"refund": {"instructions": "Is this a refund request?", "type": "choice",
"criteria": {"yes": "money back", "no": "anything else"}}}})d1:3b in detail.
d1 is a 3B decision model from Liquid AI, built on LFM2.5-VL-3B
- Published by
- LiquidAI
- Parameters
- 3.1B
- Download size
- 3.7 GB (as packaged for Ollama)
- Quantisation
- Q8_0
- Format
- gguf
- Architecture
- lfm2_vl
- Licence
- lfm1.0
- Based on
- LiquidAI/LFM2.5-VL-3B
- Task
- image text to text
- Library
- transformers
- Languages
- ar, zh, en, fr, de, hi, id, it, ja, ko, pl, pt
- First published
- 5 Oct 2026
- Last updated
- 11 Nov 2026
- Downloads (30 days)
- 25,398 on Hugging Face
- Likes
- 505
lfm2_vl image-text-to-text liquid lfm2.5 edge decision classification calibration system-one multimodal decision-model ar zh en fr de
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
Try LFM • Docs • Discord
d1-3B
d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.
- Best decision model under 10B on the Decision Index 0.2.1: 48.57, ahead of every 4B and 9B model
and of Decider 35B-A3B (47.11).
- Multimodal: images and text in the same state. It scores 74.1 on 11 public image benchmarks
(LFM2.5-VL-3B: 73.9).
- Fast: 8 ms a decision on an NVIDIA RTX 4090, 9 ms on an AMD MI325X, 30 ms on an Apple M5 Pro.
Find more information about open d1 in our blog post.
[!NOTE] 💻 Demos: Try d1-3B in a Hugging Face space without any setup: Open d1 Arcade: Collection of 10 demos using d1-3B
🗒️ Model Details
| Model | Parameters | Description |
|---|---|---|
| LFM2.5-VL-3B | 3.1B | General-purpose vision-language model (base) |
| **d1-3B** | 3.1B | Post-trained for single-pass, calibrated decisions |
d1-3B is a multimodal decision model with the following features:
- Total parameters: 3.12B
- Vision encoder: SigLIP2 NaFlex shape-optimized 400M
- Context length: 32,768 tokens
- Vocabulary size: 128,000
We recommend d1-3B wherever a pipeline needs a yes/no, a pick from named options, or a rating: routing and triage, moderation, intent and topic classification, extraction checks, reranking, LLM-as-a-judge scoring, agent guardrails, and visual inspection. It is not a chat model and does not write text.
🏃 How to use
Install the dependencies (requires transformers>=5.14):
pip install "transformers>=5.14" torch torchvision pillow
The model ships its own code, so load it with trust_remote_code=True:
import torch
from transformers import AutoModel
from transformers.image_utils import load_image
device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
dtype = torch.float32 if device == "cpu" else torch.bfloat16
model = AutoModel.from_pretrained("LiquidAI/d1-3B", trust_remote_code=True, dtype=dtype).to(device)
### Text: several named questions over one state, answered in one pass
questions = {
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?",
},
"team": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {
"billing": "Charges, refunds, invoices",
"technical": "App or site faults",
"fraud": "Suspected unauthorised use",
},
},
"urgency": {
"type": "score",
"instructions": "How urgent is this?",
"criteria": ["Can wait", "Today", "Blocking the customer now"],
},
}
print(model.system_one("I was charged twice this month, please refund one of them.", questions))
### Image: the photo is the whole state
image = load_image("http://images.cocodataset.org/val2017/000000039769.jpg") # two cats on a sofa
cats = {
"type": "choice",
"instructions": "How many cats are there?",
"criteria": {"one": "One", "two": "Two", "more": "Three or more"},
}
print(model.system_one(None, {"cats": cats}, images=[image]))
Read the rest of the model card
Batch: many requests, packed together with no padding
tickets = ["Where is my parcel? It was due Monday.", "The app crashes when I open settings."] print(model.system_one_batch([(t, {"team": questions["team"]}) for t in tickets]))
| call | |
|---|---|
| `system_one(state, questions, images=None)` | Named questions over one state, in one pass. The state and its images are read once for all questions. |
| `system_one_batch([(state, questions[, images]), ...])` | Many requests, packed with no padding. |
A state is a string, any JSON value, or `None` when the images are the whole state.
### Questions and answers
Questions follow the Decision Index schema: `type`, `instructions`, and `criteria`.
| `type` | `criteria` | answer fields |
|---|---|---|
| `noul`: yes or no | optional: `{"true": "...", "false": "..."}` to define each side | `noul`: P(yes) |
| `choice`: one of named options | `{name: description}` | `choice`, `confidence`, `probabilities` |
| `score`: 2 to 10 ordered levels | a list of level descriptions, lowest first | `score` (the expected level), `confidence`, `probabilities`, `legend` |
Each call returns `{"answers": {name: answer}, "usage": {"input_tokens": n, "output_tokens": 0}}`.
### ⚡ Speed
Warm calls, one request at a time: a single question, three questions over one state, a 3.4k-token
state and a 384 px image. The last column is throughput with 64 states packed into one pass.
### Edge Inference
We measure latency on an Apple M5 Pro and, in collaboration with NVIDIA, on an NVIDIA Jetson AGX Thor,
a Jetson AGX Orin 64 GB and a Jetson Orin Nano.
| | one question | 3 questions, one pass | 3.4k-token state | 384 px image | 64 states, packed |
|---|---:|---:|---:|---:|---:|
| Apple M5 Pro (`mps`) | 30 ms | 41 ms | 640 ms | 62 ms | 78 / s |
| NVIDIA Jetson AGX Thor | 16 ms | 20 ms | 220 ms | 35 ms | 262 / s |
| NVIDIA Jetson AGX Orin 64 GB | 26 ms | 35 ms | 560 ms | 83 ms | 110 / s |
| NVIDIA Jetson Orin Nano | 50 ms | 73 ms | 1640 ms | 202 ms | 38 / s |
### GPU Inference
We measure latency on an NVIDIA RTX 4090 and an AMD MI325X, in bf16, median of 20 runs.
| | one question | 3 questions, one pass | 3.4k-token state | 384 px image | 64 states, packed |
|---|---:|---:|---:|---:|---:|
| NVIDIA RTX 4090 | 8 ms | 21 ms | 102 ms | 17 ms | 475 / s |
| AMD MI325X | 9 ms | 14 ms | 44 ms | 18 ms | 1,106 / s |
On NVIDIA GPUs, `model.compile(mode="reduce-overhead")` runs single questions as CUDA graphs (the RTX 4090
row uses it). Without it, a single question takes 16 ms. The first call with a new shape pays for kernel
selection or compilation, so warm up the shapes you serve.
### 📊 Performance
All results are on public benchmarks.
### Decision Index 0.2.1
We scored d1-3B with the official scorer (not a leaderboard submission). All other rows come from the public leaderboard v0.2.1.
| Model | Size | Decision Index | Knowledge | Language | Retrieval | Tools | Arts |
|---|---:|---:|---:|---:|---:|---:|---:|
| Winnow-12B | 12B | 50.02 | 33.8 | 56.0 | 54.0 | 71.0 | 30.0 |
| **d1-3B** | **3B** | **48.57** | 23.8 | 56.4 | 52.8 | **74.5** | **36.3** |
| Decider 35B-A3B | 36B | 47.11 | 31.8 | 55.5 | 54.7 | 56.5 | 32.6 |
| JPT-9B | 9.7B | 46.89 | 31.7 | 56.7 | 44.6 | 67.0 | 28.6 |
| Decision 1.0 Lux | 9.7B | 43.49 | 30.9 | 48.0 | 50.0 | 57.2 | 26.4 |
| JPT-4B | 4.7B | 43.04 | 28.7 | 52.5 | 45.0 | 57.2 | 25.8 |
| Jet v6.2 | 4.7B | 42.60 | 28.7 | 43.9 | 48.2 | 62.9 | 27.0 |
| Decider 4B | 4.7B | 40.70 | 25.7 | 46.0 | 44.7 | 58.6 | 25.0 |
| Winnow-E4B | 8.0B | 39.89 | 22.3 | 45.1 | 43.8 | 62.5 | 22.8 |
| Decider 2B | 2.3B | 28.97 | 14.9 | 32.6 | 37.3 | 42.4 | 14.6 |
### Benchmarks as decisions
Besides the Decision Index, we added a few other internal evaluations based on public benchmarks.
| Benchmark | d1-3B | Decider 4B | Decider 2B |
|---|---:|---:|---:|
| SQuAD 2.0 | **85.3** | 76.0 | 67.7 |
| Civil Comments | 93.0 | 92.8 | **93.6** |
| MASSIVE intent | 87.3 | **88.3** | 81.1 |
| HelpSteer2 | 36.7 | **42.0** | 32.0 |
| PubMedQA | **66.0** | 63.3 | 65.7 |
| BoolQ | 86.7 | **89.0** | 87.3 |
| XNLI | 85.0 | **88.6** | 85.0 |
| PAWS-X | **76.9** | 69.8 | 59.5 |
| **Mean** | **77.1** | 76.2 | 71.5 |
d1-3B also scores 71.8 on [DecisionBench](https://huggingface.co/datasets/Hanno-Labs/decision-bench) (eng v1,
all 23,900 rows) and 69.3 on [Fast Decisions](https://huggingface.co/datasets/fastino/fast-decisions)
(dev split).
### Vision
Eleven public image benchmarks, read as decisions over each benchmark's options (at most 1,000 rows each),
compared with the base model:
| Benchmark | d1-3B | LFM2.5-VL-3B |
|---|---:|---:|
| AI2D | 79.9 | 80.9 |
| BLINK | 59.2 | 58.7 |
| CV-Bench | 82.1 | 87.6 |
| HallusionBench | 65.3 | 65.0 |
| MMBench | 84.9 | 84.3 |
| MME | 82.1 | 82.4 |
| MMStar | 59.9 | 61.2 |
| MMVP | 77.0 | 73.7 |
| POPE | 88.5 | 90.1 |
| VisualWebBench | 71.4 | 78.3 |
| VL-RewardBench | 65.0 | 50.9 |
| **Mean** | **74.1** | 73.9 |
| [ImajevBench](https://huggingface.co/datasets/mohit67890/imajev-bench) (dev and calibration, 253 rows) | 64.0 | 66.8 |
With the images removed, the same questions score 45.1, so the answers come from the images.
### 📬 Contact
- Got questions or want to connect? [Join our Discord community](https://discord.com/invite/liquid-ai)
- If you are interested in custom solutions with edge deployment, please contact [our sales team](https://www.liquid.ai/contact).
### Citation
@article{liquidAI2026opend1, author = {Liquid AI}, title = {Open d1: Edge decision models for text, vision, and audio}, journal = {Liquid AI Blog}, year = {2026}, note = {https://www.liquid.ai/blog/d1-open}, }
@article{liquidai2025lfm2, title = {LFM2 Technical Report}, author = {Liquid AI}, journal = {arXiv preprint arXiv:2511.23404}, year = {2025} }
Sources: LiquidAI/d1-3B on Hugging Face · d1:3b on Ollama. Collected from public sources on 14 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.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.03 | 1079 ms | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves d1:3b. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. 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.
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 d1:3b, and the platform benchmarks it on your hardware before your first request.