d1 — lokalny model AI od Liquid AI
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
Modele decyzyjne Liquid AI na urządzenia brzegowe: d1-3B (tekst i obrazy, na LFM2.5-VL-3B) oraz eksperymentalny d1-omni-600M (tekst z obrazami lub dźwiękiem). Biblioteka Pythona ładowana przez Transformers, nie serwer; licencja LFM Open License v1.0.
Warianty
Najmniejszy wariant d1 potrzebuje około 1 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV.
| Model | VRAM przy Q4 | VRAM | Kontekst | Uruchom |
|---|---|---|---|---|
| d1-3B → 3B | ~2.7 GB | 32K (32,768) | Transformers (trust_remote_code) | |
| d1-omni-600M → 600M | ~1.2 GB | 16K (16,384; 896 text tokens with images) | Transformers (trust_remote_code) |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić d1 lokalnie
Zainstaluj Ollama, a potem pobierz tag.
A Python library: you load it inside your own program. It has no HTTP server and does not run in Ollama.
Wybierz rozmiar powyżej, aby zobaczyć jego VRAM, szacowaną szybkość i polecenie instalacji.
Licencja
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Dotyczy: d1-3B, d1-omni-600MPolecane GPU
Najtańsze GPU z naszego katalogu, które uruchomi d1 lokalnie (min. 1 GB VRAM), to Intel Arc B570 (10 GB).
d1 — najczęściej zadawane pytania
How much VRAM does d1 need?
d1 needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: d1-3B (3 GB, Q4_K_M); d1-omni-600M (1 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run d1 on an RTX 4090 (24 GB)?
Yes — d1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for d1?
Q4_K_M is the best balance of quality and VRAM for d1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run d1 locally?
d1 is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.