d1-2B-GGUF Text, Image, and Video Decision-Making Model: 4GB+ VRAM

At a Glance
| Item | Value |
|---|---|
| Repository | LiquidAI/d1-2B-GGUF |
| Publisher guide | Liquid AI: models and licenses |
| Published | 2026-10-28 |
| License | lfm1.0 |
| Formats | GGUF |
| Source type | Primary source (the publisher itself) |
Values determined by this site’s code when the information was collected. Dates are JST.
Overview
LiquidAI has released the GGUF version of “d1-2B", a model aimed at decision-making (Decision) for text, images, and video. This model is built based on LFM3-VL-2B and is designed as a “decision model" that returns calibrated answers in a single forward pass rather than generating tokens.
Specifications
Specifications of the base model d1-2B are as follows:
- Parameters: 1.92B
- Architecture: LFM3 backbone, 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
- Context length: 128K tokens
Performance
Benchmark results regarding the performance of the base model are shown below. Other models in the same series (d1-omni 600M, d1-Omni 2B, d1 3B) are listed for comparison.
→ Scroll horizontally to see all columns
| Benchmark | d1 2B | d1-omni 600M | d1-Omni 2B | d1 3B |
|---|---|---|---|---|
| Decisions | ||||
| Decision Index public suite (v0.3) | 51.1 | 18.3 | 49.0 | 49.0 |
| DecisionBench (Hanno Labs) v1 | 77.1 | 58.7 | 76.4 | 73.1 |
| Decision Bench (decisionbench.ai) v4 | 85.2 | 57.9 | 84.7 | 83.6 |
| Fast Decisions | 58.8 | – | 56.8 | 59.3 |
| JevBench v1.4.1 | 77.9 | 58.0 | 75.3 | 76.2 |
| ImajevBench v2.0-lite | 75.5 | 21.7 | 72.3 | 64.0 |
| WorkflowEvals | 81.6 | 48.8 | 77.1 | 74.4 |
| Typed Decisions | 61.3 | 57.5 | 63.1 | 65.0 |
| Our board (over a hundred public and private benchmarks) | 63.2 | – | 61.8 | 58.8 |
| Vision | ||||
| AI2D | 76.7 | 37.1 | 71.5 | 79.9 |
| BLINK | 66.2 | 37.7 | 63.5 | 59.2 |
| CountQA | 51.4 | 26.8 | 45.4 | 42.6 |
| CV-Bench | 86.1 | 40.8 | 84.0 | 82.1 |
| ERQA | 45.8 | 27.3 | 42.5 | 39.8 |
| HallusionBench | 72.1 | 52.6 | 67.5 | 65.3 |
| MMBench | 87.9 | 54.2 | 85.2 | 84.9 |
| MME | 85.4 | 61.0 | 83.9 | 82.1 |
| MMMU-Pro | 26.4 | 11.9 | 24.1 | 18.5 |
| MMRB2 | 54.2 | 48.3 | 52.6 | 49.5 |
| MMStar | 67.5 | 31.9 | 61.3 | 59.9 |
| MMVP | 82.7 | 54.0 | 81.3 | 77.0 |
| NaturalBench | 81.5 | 58.8 | 80.0 | 79.8 |
| POPE | 88.7 | 82.7 | 89.9 | 88.6 |
| V* | 76.4 | 35.6 | 76.4 | 73.8 |
| VisualPuzzles | 29.9 | 26.2 | 26.9 | 29.5 |
| VisualWebBench | 96.2 | 14.9 | 88.6 | 71.4 |
| VL-RewardBench | 69.3 | 48.1 | 68.8 | 65.0 |
| Average | 70.2 | 42.8 | 67.7 | 65.4 |
According to measurements by the publishers, d1-2B exhibits the highest average performance among open d1 models. In particular, it records higher scores than d1-3B in many metrics within the “Decisions" category, demonstrating superior decision-making capabilities with a smaller parameter count. It also records an extremely high score of 96.2 on “VisualWebBench" in the “Vision" category. On the other hand, d1-3B shows higher numbers in items such as “AI2D" and “Typed Decisions".
Strengths and Use Cases
This model is designed for decision-making on text, images, and video. Unlike general chat models, it specializes in quickly returning calibrated answers for specific tasks. Specifically, the following use cases are anticipated:
- Use as routing, triage, moderation, and guardrails
- Intent and topic classification
- Information extraction from documents and forms
- Judgment, re-ranking, and visual inspection
As indicated by tags such as “classification", “extraction", and “decision-model", it has strengths in information categorization and specific data extraction. It also supports multimodality, enabling tasks such as answering in a “box" format to locate objects within images or estimating quantities. It supports multiple languages, including Japanese.
Hardware Requirements
Estimated requirements (calculated by Local Model Watch) — 1.9B parameters (taken from the base model LiquidAI/d1-2B)
| Your VRAM | Quantization | File size | Est. memory needed |
|---|---|---|---|
| 4GB (laptop iGPU / phone class) | BF16 | 3.2GB | 3.9GB |
Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. Compare with other models in our VRAM quick reference. What the quantization names mean: glossary.
Can You Run It Locally?
Runs in Ollama, LM Studio and llama.cpp as-is.
It is distributed in GGUF, so no conversion is needed.
License — lfm1.0 (Commercial use allowed with conditions): LiquidAI’s LFM Open License v1.0. Commercial use is allowed, except by legal entities with annual revenue of $10 million or more (Section 5). Redistribution requires the license text and notice of changes.
Compiled by this site’s code from the published formats, converted builds we have found, and each engine’s own model registry. “Not found" means we have not seen such a build, not that none exists. License summaries are not legal advice — check the publisher’s original terms before relying on them.
Recent Models in the Same Size Class
Models with up to 4B parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site’s estimates; licenses are as stated on the model cards.
→ Scroll horizontally to see all columns
| Model | Parameters | Smallest VRAM tier | License | Our article |
|---|---|---|---|---|
| LiquidAI/d1-omni-600M | 587M | 4GB | lfm1.0 | d1-omni-600M Multimodal Decision Model: 4GB+ VRAM, GGUF Builds (2026-11-17) |
| LiquidAI/d1-3B | 3.1B | 4GB | lfm1.0 | d1-3B Vision-Language Model: 4GB+ VRAM, GGUF Builds (2026-11-17) |
| baidu/Unlimited-OCR-2 | 3.3B | 8GB | mit | Unlimited-OCR-2 Vision-Language Model: 8GB+ VRAM (2026-11-17) |
| openbmb/MiniCPM-OCR-1.0-DSpark | 297M | 4GB | apache-2.0 | MiniCPM-OCR-1.0-DSpark OCR Acceleration Draft Model: 4GB+ VRAM (2026-11-17) |
| openbmb/MiniCPM-OCR-Jev-GPTQ | 2.2B | 4GB | apache-2.0 | OpenBMB Releases Quantized Versions of MiniCPM-OCR-Jev (2026-11-17) |
How to Get It
This model is distributed in GGUF format and can be obtained through the following methods:
- Distribution format: GGUF
- Supported engine: llama.cpp
Note that support for d1-2B in llama.cpp is awaiting the merge of the pull request (ggml-org/llama.cpp#31275). When using it, it is recommended to build and use llama.cpp with the said pull request merged.
llama-server -hf LiquidAI/d1-2B-GGUF:Q8_0 -b 8192 -ub 8192
Related Articles
- LFM2.5-24B-A2B-DSpark-GGUF Text Generation Model: 4GB+ VRAM
- d1-Omni-2B-GGUF Multimodal Decision Model: 4GB+ VRAM, File List
- LFM3-Audio-2B-GGUF Audio-Text Multimodal Model: 4GB+ VRAM, File List
- LFM3-Omni-2B-MLX-4bit Multimodal Model: 4GB+ VRAM
What to Read Next
- Find models by VRAM (This model runs from the 4GB tier) → Other models that run on a 8GB GPU
- Engines that run this model → llama.cpp / Ollama
- Formats this model is available in → GGUF format guide and models
- Learn about the publisher → Liquid AI: models, licenses and articles
- Other models for the same task → Other vision-language models

