Local AI models
AI models you run on your own computer, offline and with no subscription, from the makers who train and publish them, and the most downloaded of them on Hugging Face. For each model: the size of each of its files, the memory a conversation takes, worked out from the file itself as llama.cpp reserves it, and a check of whether it fits your graphics card and RAM, or needs more than both.
Products
- LFM2.5-24B-A2B
- Qwen3.8-Flash-Next
- granite-4.2-30b
- granite-4.2-8b
- granite-4.2-3b
- Qwen3.8-27B
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- LFM2.5-2.6B
- LFM2.5-230M
- Qwen-AgentWorld-35B-A3B
- North-Mini-Code-1.0
- gemma-4-12B-it
- Qwen3.6-27B
- Qwen3.6-35B-A3B
- MemeLens-VLM
- Fanar-2-Oryx-IVU
- Fanar-2-27B-Instruct
- gemma-4-31B-it
- gemma-4-26B-A4B-it
- gemma-4-E4B-it
- gemma-4-E2B-it
- Qwen3.5-9B
- Qwen3.5-4B
- Qwen3.5-122B-A10B
- Qwen3.5-35B-A3B
- Qwen3.5-27B
- Qwen3-Coder-Next
- GLM-4.7-Flash
- Falcon-H1-Tiny-Tool-Calling-90M
- Falcon-H1-Tiny-Multilingual-100M-Instruct
- Falcon-H1-Tiny-90M-Instruct-Curriculum
- Falcon-H1-Tiny-90M-Instruct
- LFM2.5-1.2B-Instruct
- Falcon-H1R-7B
- Qwen3-VL-2B-Instruct
- Qwen3-VL-8B-Instruct
- Qwen3-VL-4B-Instruct
- Qwen3-4B-Instruct-2507
- gpt-oss-120b
- gpt-oss-20b
- Qwen3-Coder-30B-A3B-Instruct
- Qwen3-30B-A3B-Instruct-2507
- Mistral-Small-3.2-24B-Instruct-2506
- Fanar-1-9B-Instruct
- DeepSeek-R1-0528-Qwen3-8B
- Falcon-H1-34B-Instruct
- Falcon-H1-7B-Instruct
- Falcon-H1-3B-Instruct
- Falcon-H1-1.5B-Instruct
- Falcon-H1-1.5B-Deep-Instruct
- Falcon-H1-0.5B-Instruct
- Qwen3-32B
- Qwen3-30B-A3B
- Qwen3-14B
- Qwen3-8B
- Qwen3-4B
- Qwen3-1.7B
- Qwen3-0.6B
- gemma-3-1b-it
- gemma-3-12b-it
- gemma-3-4b-it
- Phi-4-mini-instruct
- LlamaLens-Native
- ALLaM-7B-Instruct-preview
- SILMA-Kashif-2B-Instruct-v1.0
- Qwen2.5-VL-7B-Instruct
- Qwen2.5-VL-3B-Instruct
- DeepSeek-R1-Distill-Qwen-7B
- Falcon3-10B-Instruct
- Falcon3-3B-Instruct
- Falcon3-1B-Instruct
- Falcon3-Mamba-7B-Instruct
- Falcon3-7B-Instruct
- Llama-3.3-70B-Instruct
- Qwen2.5-Coder-14B-Instruct
- Qwen2.5-Coder-1.5B-Instruct
- Llama-3.2-3B-Instruct
- Llama-3.2-1B-Instruct
- Qwen2.5-Coder-7B-Instruct
- Qwen2.5-32B-Instruct
- Qwen2.5-3B-Instruct
- Qwen2.5-1.5B-Instruct
- Qwen2.5-14B-Instruct
- Qwen2.5-0.5B-Instruct
- SILMA-9B-Instruct-v1.0
- Llama-3.1-8B-Instruct
- falcon-11B
- falcon-7b-instruct