Ollama
Ollama is the local runtime bundled with CSuite. Open-weight language models (and, on Apple silicon Macs, image models through a second bundled Ollama server) are downloaded once and then run entirely on your machine: no API key, no per-use fees, and your prompts and outputs never leave your computer. What you can run is gated by your hardware, and the catalog lists each model's requirements.
Text(60 models)
NVIDIA's open multimodal mixture-of-experts model (120B total, 12B active parameters) for coding, reasoning, tool use and document understanding, with image input and a 1M-token context window.
Liquid AI's mixture-of-experts reasoning model with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools.
NVIDIA's small vision-language model (8B parameters, 4B effective), post-trained from Gemma 4 E4B for fast local conversations, image understanding and multi-turn tool use; a bundled draft model speeds up generation.
Deep Reinforce's 122B MoE self-improving model (MIT) with 256K context, image input, and native tool use, the largest Ornith 1.5 size that runs on a single high-memory machine.
Prism ML's 27B vision model trained for ternary weights (-1, 0 or +1), about half the size of a standard 4-bit model at close to full-precision quality, with tool calling, thinking and a 256K context.
Prism ML's 9B vision model trained for ternary weights (-1, 0 or +1), about half the size of a standard 4-bit model at close to full-precision quality, with tool calling, thinking and a 256K context.
NVIDIA's compact vision-language model (74B total, 9B active parameters), distilled from Nemotron 3.5 Super and tuned to fit a 24 GB NVIDIA GPU for coding, reasoning and tool use.
IBM's flagship 30B foundation model — strong reasoning across business, coding, and multilingual tasks.
IBM's 8B dense foundation model for general instruction-following, RAG, and code tasks, with native tool use.
IBM's compact 3B instruction-tuned model with multilingual support, tool use, and structured JSON output.
Deep Reinforce's 35B MoE self-improving model (MIT) with 256K context, image input, and native tool use, strong across reasoning, coding, and agentic tasks.
Deep Reinforce's 9B self-improving model (MIT) with 256K context, image input, and native tool use, tuned for reasoning, coding, and agentic work.
Alibaba's 27B multimodal Qwen 3.8 model with a 256K context — substantial gains in coding, research, and long-horizon agentic tasks, with native image and video understanding.
Meta Superintelligence Labs' 30B multimodal model for always-on local agents — tuned for tool use, long tasks, and failure recovery.
NVIDIA's 30B mixture-of-experts model with 3B active parameters, built as the execution layer for always-on agents.
Poolside's 33B (3B active) MoE agentic-coding model — full-precision BF16 weights.
Poolside's 33B (3B active) MoE model for agentic coding and long-horizon local software work, with native reasoning and tool use.
Poolside's 33B (3B active) MoE agentic-coding model — Q8 quantization for higher fidelity.
Deep Reinforce's flagship 35B self-improving agentic-coding model (MIT) with 256K context — state-of-the-art open-source coding for its size.
Deep Reinforce's 9B self-improving agentic-coding model (MIT) with 256K context and native tool use.
Cohere's compact code-specialized model tuned for fast local code generation, completion, and refactoring.
Google's 12B multimodal Gemma 4 model with strong text and image understanding.
Liquid's efficient 8B Liquid Foundation Model tuned for long-context reasoning on-device.
Google's 26B mixture-of-experts model with long context and strong multimodal reasoning.
Google's flagship 31B dense model with 256K context and top-tier text and image understanding.
Google's efficient 2B multimodal model supporting text, image, and audio input.
Google's efficient 4B multimodal model — stronger reasoning than E2B with text, image, and audio.
IBM's flagship 30B dense foundation model — strong reasoning across business, coding, and multilingual tasks.
IBM's compact 3B instruction-tuned model with multilingual support, tool use, and structured JSON output.
IBM's 8B dense decoder-only foundation model for general instruction-following, RAG, and code tasks.
NVIDIA's multimodal Nemotron mixture-of-experts model unifying text and image understanding for enterprise Q&A, summarization, and document intelligence.
Alibaba's 27B multimodal Qwen 3.6 model with a 256K context and strong vision-language reasoning.
Alibaba's flagship 35B multimodal Qwen 3.6 model for top-tier vision-language reasoning.
Liquid's 24B foundation model with efficient long-context reasoning.
Alibaba's compact 2B multimodal Qwen model with vision input and a 256K context — fast on-device text+image reasoning.
Alibaba's efficient 4B multimodal Qwen model with vision input and strong multilingual reasoning.
Alibaba's 9B multimodal Qwen model balancing vision-language reasoning with on-device performance.
Google's medical multimodal model fine-tuned for healthcare and biomedical tasks.
Ai2's fully open 32B model — open weights, data, and training recipe — with long chain-of-thought reasoning.
Mistral's 14B dense edge model (Apache 2.0) tuned for fast on-device reasoning and tool use.
Mistral's compact 3B dense edge model (Apache 2.0) for fast on-device text generation and tool use.
Mistral's efficient 8B dense edge model (Apache 2.0) for on-device chat, reasoning, and tool use.
Ai2's fully open 32B model with open weights, training data, and recipe.
Ai2's fully open 7B model with open weights, training data, and recipe.
OpenAI's open-weight 20B reasoning model (Apache 2.0) with configurable reasoning effort and native tool calling — runs on 16 GB.
Large medical variant for complex clinical reasoning and biomedical analysis.
Mistral's 24B instruction-tuned model with vision input, robust function calling, and a 128K context.
DeepSeek's 8B reasoning model distilled from Qwen3 (R1-0528) with strong math, code, and logic.
Alibaba's compact 4B instruction model with strong reasoning and multilingual capabilities.
Alibaba's ultra-compact 0.6B Qwen3 model — runs in-process via HuggingFace or through Ollama, with tool use.
Microsoft's 14B reasoning model fine-tuned for chain-of-thought on math, science, and code.
Google's compact 1B Gemma 3 model — runs in-process via HuggingFace or through Ollama.
Microsoft's compact 3.8B model with a 128K context and native function calling.
DeepSeek's compact 1.5B reasoning model distilled from Qwen2.5 — chain-of-thought on-device.
DeepSeek's 14B reasoning model distilled from Qwen2.5 with exceptional math and coding benchmarks.
DeepSeek's 32B reasoning model distilled from Qwen2.5 for top-tier chain-of-thought reasoning.
Microsoft's 14B state-of-the-art open model with strong reasoning, math, and code.
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
Meta's compact 3B instruction-tuned model — fast on-device text generation.
Meta's 8B instruction-tuned model with 128K context and strong general reasoning.
Image(2 models)
Audio(1 model)
Decision(13 models)
Cloudflare's open-source 27B decision model, fine-tuned from Qwen3.8 27B to turn a state and a schema of typed questions into decisions.
The fast 9B member of Cloudflare's open-source Clef decision models, fine-tuned from Qwen3.5 9B for typed classification and routing.
Together AI's experimental decision model, fine-tuned from Qwen3.5 4B for routing, triage and policy checks, with open weights.
Convai Innovations' 421M-parameter multilingual decision model, built on ModernBERT, that answers every question in a single forward pass.
vLLM Semantic Router's 27B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
vLLM Semantic Router's 9B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
vLLM Semantic Router's 4B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
vLLM Semantic Router's 2B decision model on Qwen3.5: it reads a text or JSON state, or a still image, and answers choice, score and yes/no questions with probabilities.
Liquid AI's 600M decision model on LFM2.5-Encoder-350M, running fully offline: it answers typed questions about a text or JSON state with a choice, a score or a yes/no probability.
Strands Agents' 2B decision model for classification, routing and scoring, built on Qwen3.5 2B with a trained decision head. It runs on Apple silicon Macs and reads up to 4K tokens per question.
Perplexity's 27B decision model, a newer checkpoint of Decider V1 that reads a state and returns typed, probabilistic answers to choice, score and yes/no questions.
The 0.8B size of Together AI's experimental Tev1 decision model, a 0.8 GB download that loads faster than the 4B.
Bespoke Labs' 9B decision model, fine-tuned from Qwen3.5 for classification, triage and rubric scoring.