Can I Run LLM Model Locally?

Qwen3 Coder 30B A3B Instruct

Alibaba · 30.5B · runs from 8.8 GB

745.9K 1.2K

Qwen3 Coder 30B A3B Instruct is a code-specialized Mixture of Experts (MoE) model from Alibaba Cloud's Qwen 3 Coder series, with 30 billion total parameters and approximately 3 billion active parameters per forward pass. The MoE architecture allows it to deliver strong coding performance while keeping per-token compute costs low, making it faster at inference than comparably capable dense models. The model is instruction-tuned for programming assistance, code generation, debugging, and software engineering conversation. It requires VRAM proportional to its total 30B parameter count for loading weights, but benefits from efficient inference throughput due to its low active parameter count. Released under the Apache 2.0 license.

Chat</>Code

Qwen3.6 35B A3B

Alibaba · 36.0B · runs from 10.3 GB

4.4M 2.8K

Qwen3.6 35B A3B is a 36.0B-parameter open language model from Alibaba in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Vision

Qwen3.8 27B

Alibaba · 27.8B · runs from 12.6 GB

6.0M 14.0K

Qwen3.8 27B is a 27.8B-parameter open language model from Alibaba in the Qwen 3.8 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Vision

Qwen2.5 7B Instruct

Alibaba · 7.6B · runs from 2.7 GB

11.4M 1.6K

Qwen2.5 7B Instruct is a 7.6-billion parameter instruction-tuned model from Alibaba Cloud's Qwen 2.5 series. It supports a 128K token context window and is fine-tuned for conversational AI, instruction following, and general assistant tasks. Its efficient size makes it well-suited for local deployment on consumer GPUs with 8GB or more of VRAM. The model delivers strong performance for its parameter class across reasoning, multilingual understanding, and coding tasks. It benefits from the improved pretraining data and techniques of the Qwen 2.5 generation. Released under the Apache 2.0 license and widely supported by inference frameworks such as llama.cpp, vLLM, and Ollama.

Chat

Qwen3.6 27B

Alibaba · 27.8B · runs from 8.4 GB

5.3M 2.3K

Qwen3.6 27B is a 27.8B-parameter open language model from Alibaba in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Vision

Gemma 4 26B A4B IT

Google · 25.8B · runs from 7.7 GB

8.3M 1.5K

Gemma 4 26B A4B IT is a 25.8B-parameter open language model from Google in the Gemma 4 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.

Vision