Llama
Llama 3.2 3B
Meta · 3B parameters · 2 GGUF variants
chatlightweightRAG
Open model →Local AI model catalog
Local AI models for PC and Mac fit planning.
Browse model families, GGUF quantizations, and conservative memory planning signals used by AIPCFit. Model pages link to dedicated GPU memory guides and Apple Silicon unified-memory guides where the fit engine has enough information.
Starting from a model and quantization? Estimate memory planning thresholds with the LLM VRAM calculator.
Browse by family
Explore model families
Model finder
Find a local AI model
Search the catalog or narrow models by family, size, and common local-AI use case.
20 of 20 models
small
Llama
Llama 3.1 8B
Meta · 8B parameters · 2 GGUF variants
chatcodingRAG
Open model →Llama
Llama 3.3 70B
Meta · 70B parameters · 1 GGUF variant
chatreasoning
Open model →Qwen
Qwen3 4B
Alibaba Cloud · 4B parameters · 2 GGUF variants
chatlightweightRAG
Open model →Qwen
Qwen3 8B
Alibaba Cloud · 8B parameters · 2 GGUF variants
chatcodingRAG
Open model →Qwen
Qwen3 14B
Alibaba Cloud · 14B parameters · 2 GGUF variants
chatcodingreasoning
Open model →Qwen
Qwen3 30B-A3B
Alibaba Cloud · 30.5B parameters · 2 GGUF variants
chatcodingreasoningRAG
Open model →Qwen
Qwen3.8 27B
Alibaba Cloud · 27B parameters · 2 GGUF variants
chatcodingreasoningRAG
Open model →Gemma
Gemma 3 4B
Google · 4B parameters · 2 GGUF variants
chatlightweightRAG
Open model →Gemma
Gemma 3 12B
Google · 12B parameters · 2 GGUF variants
chatreasoningRAG
Open model →Gemma
Gemma 3 27B
Google · 27B parameters · 2 GGUF variants
chatreasoning
Open model →Mistral
Mistral 7B
Mistral AI · 7B parameters · 2 GGUF variants
chatcodinglightweight
Open model →Mistral
Mixtral 8x7B
Mistral AI · 46.7B parameters · 1 GGUF variant
chatcodingreasoning
Open model →Mistral
Mistral Small 3.2 24B
Mistral AI · 24B parameters · 2 GGUF variants
chatcodingreasoningRAG
Open model →DeepSeek
DeepSeek-R1 Distill Qwen 7B
DeepSeek · 7B parameters · 2 GGUF variants
reasoningchatcoding
Open model →DeepSeek
DeepSeek-R1 Distill Qwen 14B
DeepSeek · 14B parameters · 1 GGUF variant
reasoningcodingchat
Open model →DeepSeek
DeepSeek-R1 Distill Qwen 32B
DeepSeek · 32B parameters · 2 GGUF variants
reasoningcodingchat
Open model →Phi
Phi-3.5 Mini
Microsoft · 3.8B parameters · 1 GGUF variant
chatlightweightcoding
Open model →Phi
Phi-4 Mini
Microsoft · 3.8B parameters · 1 GGUF variant
chatlightweightcoding
Open model →Phi
Phi-4
Microsoft · 14B parameters · 1 GGUF variant
chatreasoningcoding
Open model →