Open-weight models,
sovereign UK infrastructure

Frontier reasoning, open weights

Qwen 3.6 is Alibaba's flagship open-weight model, built for agentic work with strong multilingual reasoning, native tool use, and image understanding. It offers a hybrid thinking mode that can reason at length or answer directly, and handles 262K-token contexts, making it a capable all-rounder for chat, coding, and document tasks.

Alibaba’s flagship multimodal family

OpenAI’s open-weight release

Google DeepMind’s efficient multimodal family

Purpose-built for code

Meta’s 70B workhorse

Qwen 3 VL is Alibaba's vision-language model, pairing Qwen 3's reasoning and tool use with detailed image understanding. It reads charts, documents, and photos alongside text and offers an explicit thinking mode, making it well suited to multimodal analysis and agentic tasks.

Llama 4 Scout is Meta's natively-multimodal mixture-of-experts model, activating 17B parameters per token from a larger expert pool for efficient inference. It reads images as well as text and supports an exceptionally long, million-token context, aimed at long-document and multimodal workloads.

Phi-4 is Microsoft's small-but-capable model, trained with a heavy emphasis on high-quality and synthetic data to punch above its size on reasoning tasks. Its compact footprint makes it a practical choice for cost-sensitive and on-device deployments.

Qwen 3 Coder Next is Alibaba's next-generation coding model, built on a hybrid architecture for efficient long-context inference. It targets agentic, repository-scale software tasks and tool use across a 262K-token context.

GLM 4.7 Flash is Z.ai's fast, lightweight model in the GLM 4 line, offering a hybrid reasoning mode that trades depth for speed on demand. It's tuned for tool use and responsive agentic workflows across a roughly 200K-token context.

Ministral 3 is Mistral AI's compact instruction model family, offered in several sizes with tool use and image understanding. It's engineered for efficient, low-latency inference on modest hardware while retaining strong general capability, making it a good edge and on-device option.

Devstral Small 2 is Mistral AI's coding-focused model, tuned for software-engineering agents that navigate and edit real codebases. It combines tool use with image understanding in a compact 24B size, targeting practical developer automation.

GLM OCR is Z.ai's document-understanding model, specialised for optical character recognition and structured extraction from images and scanned pages. It reads dense layouts and returns clean, machine-usable text across a 131K-token context.

Mistral Small 4 is Mistral AI's mid-size flagship, a mixture-of-experts model that activates only a small fraction of its parameters per token for efficient inference. It reads images as well as text, supports tool use, and handles a 256K-token context, making it a capable all-rounder for chat, coding, and document work.

LFM 2.5 is Liquid AI's efficient model family built on a liquid-foundation architecture designed for fast on-device inference. It includes a mixture-of-experts variant and supports tool use, targeting responsive assistants that run well on constrained hardware.

Devstral 2 is Mistral AI's large coding model, built for software-engineering agents that explore and modify real repositories rather than answer isolated questions. At 123B dense parameters with a 256K-token context and native tool use, it targets long-running agentic development work. It ships under a modified MIT licence that permits commercial use.

LFM 2.5 VL is Liquid AI's compact vision-language model, adding image understanding to the efficient LFM 2.5 line. Its small footprint suits multimodal assistants that need to run on-device or at low latency.

Nemotron 3 Nano is NVIDIA's small, efficient model tuned for reasoning and tool use, offered in dense and mixture-of-experts sizes. It's built for cost-effective agentic deployments and supports a 131K-token context.

Granite 4.0 Micro is IBM's smallest enterprise model, a hybrid design tuned for tool use and reliable instruction following. Its compact size and permissive licensing make it a practical fit for on-device and cost-sensitive business applications.

Magistral Small is Mistral AI's reasoning model, trained to work through problems step by step before answering. It now reads images as well as text, extending that deliberate reasoning to visual input. At a compact 24B size it brings transparent reasoning and tool use within reach of single-GPU deployments.

GLM 4.6V Flash is Z.ai's fast vision-language model, pairing image understanding with responsive, lightweight inference. It's suited to multimodal chat and analysis where latency matters, across a 131K-token context.

Mistral Large 3 is Mistral AI's frontier open-weight model, a mixture-of-experts design that activates a fraction of its parameters per token so inference cost tracks the active size rather than the full one. It reads images as well as text, uses tools natively, and handles a 256K-token context for demanding reasoning and long-document work.

MiMo V2.5 is Xiaomi's open model tuned for reasoning, tool use, and image understanding. It offers an explicit thinking mode and targets capable multimodal assistance in an efficient package.

Voxtral Small is Mistral AI's speech-understanding model: it takes spoken audio directly as input alongside text, so you can ask questions about a recording rather than transcribing it first. Built on the Mistral Small 24B backbone, it handles a 131K-token context and targets voice assistants and audio analysis.

Ornith 1.0 is DeepReinforce's hybrid-reasoning model, designed to combine deliberate step-by-step thinking with efficient long-context inference. It supports tool use and is offered in two sizes for different quality-versus-cost trade-offs.

DeepSeek OCR is DeepSeek's document-understanding model, specialised for optical character recognition and extracting text from images and scans. It focuses on accurate, structured reading of visual documents.

DeepSeek R1 Distill is a family of smaller models distilled from DeepSeek R1's reasoning traces onto Qwen and Llama backbones. They bring much of R1's step-by-step reasoning to sizes that run on modest hardware.

dots.ocr is Rednote's document-parsing model, built to read complex layouts — tables, columns, and mixed text — and return structured output. It targets accurate OCR and document understanding across a 131K-token context.

BGE Reranker v2 m3 is BAAI's multilingual reranking model, scoring how well each candidate document answers a query to sharpen retrieval results. It's a lightweight, effective second stage for RAG pipelines across many languages.

Whisper is OpenAI's speech-to-text model, transcribing audio across many languages with strong robustness to accents and background noise. The large-v3 and faster large-v3-turbo variants suit everything from meeting notes to media captioning.

FLUX.1 [schnell] is Black Forest Labs' fast text-to-image model, distilled to generate high-quality images in just a few diffusion steps. Its speed and permissive Apache-2.0 licence make it a strong default for quick drafts and interactive generation.

Z-Image Turbo is Alibaba's distilled text-to-image model built for speed, producing images in only a few diffusion steps. It trades some peak fidelity for near-interactive latency, making it a good default for fast drafts and previews.

SDXL Turbo is Stability AI's real-time text-to-image model, distilled from SDXL to generate images in as little as one to four steps. It's ideal for interactive and preview use where speed matters most.

FLUX.2 [klein] is Black Forest Labs' efficient text-to-image model, offered in 4B and 9B sizes for a choice of speed versus fidelity. It brings the FLUX.2 line's image quality to hardware that can't run the largest checkpoints. Note that the two sizes ship under different terms: the 4B is Apache-2.0, while the 9B is released under the FLUX Non-Commercial License and is not licensed for commercial use.

Qwen-Image 2512 is Alibaba's high-fidelity text-to-image model, notable for rendering legible text within images. It targets detailed, prompt-faithful generation for design and content work.

Stable Diffusion 3.5 Large Turbo is Stability AI's distilled flagship text-to-image model, generating high-quality images in a handful of steps. It pairs the detail of SD 3.5 Large with fast, few-step inference.

nomic-embed-text v1.5 is Nomic AI's open text-embedding model, producing high-quality vectors for search, retrieval, and RAG. It supports adjustable embedding dimensions via Matryoshka representation, letting you trade vector size for cost.

Qwen 3 Embedding is Alibaba's text-embedding family built on Qwen 3, offered in several sizes for search and retrieval. It delivers strong multilingual embeddings for RAG and semantic-search pipelines across a 32K-token context.

BGE-M3 is BAAI's versatile embedding model supporting dense, sparse, and multi-vector retrieval in a single model. It handles more than 100 languages and long inputs, making it a strong multilingual default for search and RAG.

EmbeddingGemma is Google DeepMind's compact text-embedding model from the Gemma family, tuned for on-device retrieval. Its small size and strong multilingual quality make it a practical embedder for local RAG and semantic search.