gemma4

Google

قابل اجرا روی RAM

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

qwen3.5

Alibaba

قابل اجرا روی RAM

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

qwen3-vl

Alibaba

قابل اجرا روی RAM

The most powerful vision-language model in the Qwen model family to date.

qwen3

Alibaba

قابل اجرا روی RAM

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

nemotron-3-nano

NVIDIA

قابل اجرا روی RAM

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

deepseek-r1

DeepSeek

قابل اجرا روی RAM

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

ministral-3

Mistral AI

قابل اجرا روی RAM

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

granite4

IBM

قابل اجرا روی RAM

Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

LFM2.5 is a new family of hybrid models designed for on-device deployment.

LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.

llama3.2

Meta

قابل اجرا روی RAM

Meta's Llama 3.2 goes small with 1B and 3B models.

functiongemma

Google

قابل اجرا روی RAM

FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

qwen2.5

Alibaba

قابل اجرا روی RAM

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

The current, most capable model that runs on a single GPU.

qwen2.5-coder

Alibaba

قابل اجرا روی RAM

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

mistral

Mistral AI

قابل اجرا روی RAM

The 7B model released by Mistral AI, updated to version 0.3.

qwen2

Alibaba

قابل اجرا روی RAM

Qwen2 is a new series of large language models from Alibaba group

granite3.1-moe

IBM

قابل اجرا روی RAM

The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

granite4.1

IBM

قابل اجرا روی RAM

IBM Granite Models are a family of enterprise-ready, open foundation models that support multilingual capabilities, coding, retrieval-augmented generation (RAG), tool use, and structured JSON output. Released under Apache 2.0 license.

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

granite3-moe

IBM

قابل اجرا روی RAM

The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.

granite4.1-guardian

IBM

قابل اجرا روی RAM

Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.

phi4-mini

Microsoft

قابل اجرا روی RAM

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.