As of October 7, 2026, Liquid AI’s official d1 launch material documents access through its API, console, and playground—not downloadable d1 weights or a local installation path. You can try d1 through the official launch post; if you need local inference, treat other Liquid Foundation Models as a separate option and verify their specific model details.
Can you run Liquid AI d1 locally?
Not on the evidence in Liquid AI’s October 5, 2026 launch post. It describes d1 access through the Liquid AI API, console, and playground, but does not provide downloadable d1 weights or local setup instructions. Liquid AI says open weights for upcoming models are planned; that is a future-facing statement, not confirmation that d1 weights are currently available.
Liquid AI’s broader Liquid Foundation Models (LFM) catalogue describes models designed for local deployment across CPUs, GPUs, and NPUs. Those family-level capabilities do not establish that d1 itself can be downloaded or run locally. Check the individual model card, license, runtime support, and hardware requirements before choosing an LFM for an offline project.
How d1 makes decisions
Liquid AI describes d1 as a decision model that accepts unstructured text, images, or both, along with one or more questions. It processes the input in one forward pass and returns probabilities for possible answers rather than generating tokens. In practical terms, you provide the situation, ask a question, and define the outcomes you want it to consider; then you inspect the probabilities it assigns.
#1 Best Overall
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
The launch post establishes this high-level interface but does not establish an exact API request schema or endpoint. Use the current official console, playground, or API documentation for request details rather than relying on guessed parameters or example code.
How to test d1’s decision-making
1. Define the decision and candidate outcomes
Start with one real task, such as classifying a support request or identifying an object in an image. Write the question and define a fixed set of candidate outcomes before running the model. Make labels mutually understandable and include an appropriate uncertainty or “other” outcome when the task requires one.
Rank #2
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
2. Freeze a small evaluation set
Collect examples representative of the intended use. Keep the examples, candidate labels, and reference answers unchanged throughout the evaluation. Include ordinary cases, ambiguous cases, and edge cases, and record how many examples belong to each group. This makes it possible to distinguish a broad performance problem from an error concentrated in a difficult category.
3. Record the outputs and errors
For each example, save the input, question, candidate outcomes, returned probabilities, and reference answer. Count incorrect decisions and inspect which labels are confused. If you change the wording, examples, or outcome set, treat that as a new test run rather than mixing results.
Rank #3
- EVOLUTION RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
4. Choose metrics that match the task
- Binary classification: report precision, recall, and F1 when the relative costs of false positives and false negatives matter.
- Multiple-choice decisions: report accuracy and a confusion matrix so readers can see which outcomes are mistaken for others.
- Probability-sensitive applications: assess calibration separately. A model’s assigned probabilities are not automatically reliable confidence estimates.
State the dataset, label definitions, scoring rule, and number of examples with the results. These are recommended evaluation practices, not d1-specific published scores.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What Liquid AI has reported about d1
Liquid AI’s October 5, 2026 launch post reports the following results. They are company-reported examples, not independent validation:
| Example | Liquid AI’s reported result | Qualification |
|---|---|---|
| Wordle | 12 of 12 games solved, averaging 3.8 guesses | Reported by Liquid AI in its 2026 launch post. |
| Quick, Draw! | 5.2 of 6 doodles recognized | The post says random guessing gets 0.6. |
| Tetris | 70 to 81 lines when supplied with a screen image | The post compares this with describing the game in text alone. |
| Cost across six applications | 19× to 200× lower than the two named comparison models | The company used d1 input-token list pricing of $0.04 per million tokens, without prompt-cache discounts, and up to eight requests in flight. This is not a general price guarantee. |
The six-application comparison was run once per model on October 5, 2026, using Liquid AI’s Playground comparison script and its model-specific setup and list-price assumptions. The post notes that some code questions and compaction sessions were written after d1’s pipeline was set. For visual inspection, each model saw a good part from the same line beside the part being inspected. Treat the comparison as vendor-reported, not an independently replicated benchmark.
No independent d1 replication study or fully reproducible public protocol for that launch comparison is established in the cited materials. The reported figures are useful examples of tasks Liquid AI says d1 can handle, but they do not by themselves show how it will perform on a different dataset or operational setting.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →If local inference is a requirement
Look at the specific model you intend to deploy in Liquid AI’s LFM catalogue rather than assuming d1 is locally available. Confirm its weights, license, runtime, supported hardware, and model-specific documentation before building around it.
Liquid AI’s Pipette documentation also cautions that a quality score displayed alongside phone-performance information does not mean the quality evaluation ran on that phone. Read device-performance and quality figures as separate evidence unless the documentation explicitly connects them.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
