Providers · Local runtime
Ollama
Ollama is the local runtime bundled with CSuite. Open-weight language and image models are downloaded once and then run entirely on your machine — no API key, no per-use fees, and nothing leaves your computer. What you can run is gated by your hardware, and the catalog lists each model's requirements.
Text(53 models)
Granite 4.2 30B
IBM's flagship 30B foundation model — strong reasoning across business, coding, and multilingual tasks.
1 month ago (Aug 2026)
Granite 4.2 8B
IBM's 8B dense foundation model for general instruction-following, RAG, and code tasks, with native tool use.
1 month ago (Aug 2026)
Granite 4.2 3B
IBM's compact 3B instruction-tuned model with multilingual support, tool use, and structured JSON output.
1 month ago (Aug 2026)
Ornith 1.5 35B
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.
1 month ago (Aug 2026)
Ornith 1.5 9B
Deep Reinforce's 9B self-improving model (MIT) with 256K context, image input, and native tool use, tuned for reasoning, coding, and agentic work.
1 month ago (Aug 2026)
Qwen3.8 27B
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.
1 month ago (Aug 2026)
Muse Glimmer
Meta Superintelligence Labs' 30B multimodal model for always-on local agents — tuned for tool use, long tasks, and failure recovery.
1 month ago (Aug 2026)
Nemotron 3.5 Lightning
NVIDIA's 30B mixture-of-experts model with 3B active parameters, built as the execution layer for always-on agents.
1 month ago (Aug 2026)
Laguna XS 2.1 (BF16)
Poolside's 33B (3B active) MoE agentic-coding model — full-precision BF16 weights.
2 months ago (Jul 2026)
Laguna XS 2.1 (Q4)
Poolside's 33B (3B active) MoE model for agentic coding and long-horizon local software work, with native reasoning and tool use.
2 months ago (Jul 2026)
Laguna XS 2.1 (Q8)
Poolside's 33B (3B active) MoE agentic-coding model — Q8 quantization for higher fidelity.
2 months ago (Jul 2026)
Ornith 35B
Deep Reinforce's flagship 35B self-improving agentic-coding model (MIT) with 256K context — state-of-the-art open-source coding for its size.
3 months ago (Jun 2026)
Ornith 9B
Deep Reinforce's 9B self-improving agentic-coding model (MIT) with 256K context and native tool use.
3 months ago (Jun 2026)
North Mini Code 1 (Q4)
Cohere's compact code-specialized model tuned for fast local code generation, completion, and refactoring.
3 months ago (Jun 2026)
Gemma 4 12B
Google's 12B multimodal Gemma 4 model with strong text and image understanding.
3 months ago (Jun 2026)
LFM2.5 8B
Liquid's efficient 8B Liquid Foundation Model tuned for long-context reasoning on-device.
4 months ago (May 2026)
Gemma 4 26B (MoE)
Google's 26B mixture-of-experts model with long context and strong multimodal reasoning.
5 months ago (Apr 2026)
Gemma 4 31B
Google's flagship 31B dense model with 256K context and top-tier text and image understanding.
5 months ago (Apr 2026)
Gemma 4 E2B
Google's efficient 2B multimodal model supporting text, image, and audio input.
5 months ago (Apr 2026)
Gemma 4 E4B
Google's efficient 4B multimodal model — stronger reasoning than E2B with text, image, and audio.
5 months ago (Apr 2026)
Granite 4.1 30B
IBM's flagship 30B dense foundation model — strong reasoning across business, coding, and multilingual tasks.
5 months ago (Apr 2026)
Granite 4.1 3B
IBM's compact 3B instruction-tuned model with multilingual support, tool use, and structured JSON output.
5 months ago (Apr 2026)
Granite 4.1 8B
IBM's 8B dense decoder-only foundation model for general instruction-following, RAG, and code tasks.
5 months ago (Apr 2026)
Nemotron 3
NVIDIA's multimodal Nemotron mixture-of-experts model unifying text and image understanding for enterprise Q&A, summarization, and document intelligence.
5 months ago (Apr 2026)
Qwen3.6 27B
Alibaba's 27B multimodal Qwen 3.6 model with a 256K context and strong vision-language reasoning.
5 months ago (Apr 2026)
Qwen3.6 35B
Alibaba's flagship 35B multimodal Qwen 3.6 model for top-tier vision-language reasoning.
5 months ago (Apr 2026)
LFM2 24B
Liquid's 24B foundation model with efficient long-context reasoning.
7 months ago (Feb 2026)
Qwen3.5 2B
Alibaba's compact 2B multimodal Qwen model with vision input and a 256K context — fast on-device text+image reasoning.
7 months ago (Feb 2026)
Qwen3.5 4B
Alibaba's efficient 4B multimodal Qwen model with vision input and strong multilingual reasoning.
7 months ago (Feb 2026)
Qwen3.5 9B
Alibaba's 9B multimodal Qwen model balancing vision-language reasoning with on-device performance.
7 months ago (Feb 2026)
Gemma 3 Med 4B
Google's medical multimodal model fine-tuned for healthcare and biomedical tasks.
8 months ago (Jan 2026)
OLMo 3.1 32B
Ai2's fully open 32B model — open weights, data, and training recipe — with long chain-of-thought reasoning.
9 months ago (Dec 2025)
Ministral 3 14B
Mistral's 14B dense edge model (Apache 2.0) tuned for fast on-device reasoning and tool use.
9 months ago (Dec 2025)
Ministral 3 3B
Mistral's compact 3B dense edge model (Apache 2.0) for fast on-device text generation and tool use.
9 months ago (Dec 2025)
Ministral 3 8B
Mistral's efficient 8B dense edge model (Apache 2.0) for on-device chat, reasoning, and tool use.
9 months ago (Dec 2025)
OLMo 3 32B
Ai2's fully open 32B model with open weights, training data, and recipe.
10 months ago (Nov 2025)
OLMo 3 7B
Ai2's fully open 7B model with open weights, training data, and recipe.
10 months ago (Nov 2025)
GPT-OSS 20B
OpenAI's open-weight 20B reasoning model (Apache 2.0) with configurable reasoning effort and native tool calling — runs on 16 GB.
1 year ago (Aug 2025)
Gemma 3 Med 27B
Large medical variant for complex clinical reasoning and biomedical analysis.
1 year ago (Jul 2025)
Mistral Small 3.2 24B
Mistral's 24B instruction-tuned model with vision input, robust function calling, and a 128K context.
1 year ago (Jun 2025)
R1 8B
DeepSeek's 8B reasoning model distilled from Qwen3 (R1-0528) with strong math, code, and logic.
1 year ago (May 2025)
Qwen3 4B
Alibaba's compact 4B instruction model with strong reasoning and multilingual capabilities.
1 year ago (Apr 2025)
Qwen3 0.6B
Alibaba's ultra-compact 0.6B Qwen3 model — runs in-process via HuggingFace or through Ollama, with tool use.
1 year ago (Apr 2025)
Phi-4 Reasoning 14B
Microsoft's 14B reasoning model fine-tuned for chain-of-thought on math, science, and code.
1 year ago (Apr 2025)
Gemma 3 1B
Google's compact 1B Gemma 3 model — runs in-process via HuggingFace or through Ollama.
1 year ago (Mar 2025)
Phi-4 Mini 3.8B
Microsoft's compact 3.8B model with a 128K context and native function calling.
1 year ago (Feb 2025)
R1 1.5B
DeepSeek's compact 1.5B reasoning model distilled from Qwen2.5 — chain-of-thought on-device.
1 year ago (Jan 2025)
R1 14B
DeepSeek's 14B reasoning model distilled from Qwen2.5 with exceptional math and coding benchmarks.
1 year ago (Jan 2025)
R1 32B
DeepSeek's 32B reasoning model distilled from Qwen2.5 for top-tier chain-of-thought reasoning.
1 year ago (Jan 2025)
Phi-4 14B
Microsoft's 14B state-of-the-art open model with strong reasoning, math, and code.
1 year ago (Dec 2024)
Llama 3.2 1B
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
2 years ago (Sep 2024)
Llama 3.2 3B
Meta's compact 3B instruction-tuned model — fast on-device text generation.
2 years ago (Sep 2024)
Llama 3.1 8B
Meta's 8B instruction-tuned model with 128K context and strong general reasoning.
2 years ago (Jul 2024)