Model Library
Ready-to-go open models, pre-configured for one RTX 5090. Click Deploy, pick a GPU, and get an API or web UI in minutes — or bring your own model with a template.
Featured models
Qwen3 8B
Dense 8B model with switchable thinking / non-thinking modes, strong multilingual chat and tool use.
Qwen3 32B (AWQ)
The flagship dense Qwen3, 4-bit AWQ quantised to run on a single RTX 5090.
gpt-oss 20B
OpenAI's open-weight reasoning model with adjustable reasoning effort, in a ready-to-use chat UI.
FLUX.1 [schnell]
Fast 12B text-to-image model — high-quality images in 1–4 steps, free for commercial use.
Wan 2.1 Text-to-Video 1.3B
Lightweight open text-to-video model — 480p clips on a single GPU in minutes.
Whisper Large v3
Best-in-class open speech recognition for ~100 languages, behind an OpenAI-compatible API.
Text generation
Qwen3 8B
Dense 8B model with switchable thinking / non-thinking modes, strong multilingual chat and tool use.
Qwen3 14B (FP8)
Larger Qwen3 in official FP8 weights — noticeably stronger reasoning while fitting comfortably on one GPU.
Qwen3 32B (AWQ)
The flagship dense Qwen3, 4-bit AWQ quantised to run on a single RTX 5090.
Qwen2.5 72B Instruct (AWQ)
A 70B-class model split across both GPUs of a 2× RTX 5090 machine (64 GB VRAM) with tensor parallelism.
Reasoning
Qwen3 8B
Dense 8B model with switchable thinking / non-thinking modes, strong multilingual chat and tool use.
Qwen3 14B (FP8)
Larger Qwen3 in official FP8 weights — noticeably stronger reasoning while fitting comfortably on one GPU.
Qwen3 32B (AWQ)
The flagship dense Qwen3, 4-bit AWQ quantised to run on a single RTX 5090.
Qwen2.5 72B Instruct (AWQ)
A 70B-class model split across both GPUs of a 2× RTX 5090 machine (64 GB VRAM) with tensor parallelism.
Coding
Multimodal
Gemma 3 12B
Google's multimodal open model — understands images and text, 140+ languages.
Gemma 3 27B (Ollama)
Google's largest Gemma 3 in 4-bit with a chat UI — multimodal and multilingual.
Image generation
FLUX.1 [schnell]
Fast 12B text-to-image model — high-quality images in 1–4 steps, free for commercial use.
FLUX.1 [dev]
Higher-quality guidance-distilled FLUX model for detailed images — non-commercial licence.
Stable Diffusion XL 1.0
The classic 1024px image model with the largest ecosystem of LoRAs, ControlNets and fine-tunes.
Video generation
Audio
Whisper Large v3
Best-in-class open speech recognition for ~100 languages, behind an OpenAI-compatible API.
Distil-Whisper Large v3
Distilled Whisper — several times faster than large-v3 for English with close accuracy.