Kimi K2 · Ollama

kimi-k2.7-code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.

vision tools thinking cloud

229.2K Pulls 1 Tag Updated 2 months ago

kimi-k2.6

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

vision tools thinking cloud

455.1K Pulls 1 Tag Updated 4 months ago

aratan/qwen3.7-35b-q4

No Oficial 29 t/s en 8 VRAM - Calidad a escala fronteriza como GPT-5.5, DeepSeek-V4-pro y Kimi-K2.6.

vision tools

939 Pulls 1 Tag Updated 1 month ago

hadad/qwen3-4bd

Qwen3 fine-tuned using an ultra massive distilled dataset derived from a range of powerful AI models, including Kimi K2.5, Qwen 3.5, Claude Opus 4.6, Claude Opus 4.5, Gemini 3 Pro, Claude Haiku 4.5, GPT 5.2, Gemini 3.1 Pro, GLM 4.7, GLM 5 .......

tools thinking

521 Pulls 2 Tags Updated 4 months ago

huihui_ai/kimi-k2-abliterated

A state-of-the-art mixture-of-experts (MoE) language model. Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.

tools 1026b

888 Pulls 6 Tags Updated 8 months ago

frob/kimi-k2.5-prism-reap

50% REAP expert-pruned version of moonshotai/Kimi-K2.5, built from the PRISM variant.

vision tools thinking

168 Pulls 3 Tags Updated 6 months ago

huihui_ai/kimi-k2

This is not the ablation version. Kimi-K2-Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.

tools 1026b

12.2K Pulls 4 Tags Updated 1 year ago