#1
LFM2.5-8B-A1B
Liquid AI hybrid model built for on-device assistants. 8.3B total / 1.5B active, 128K context, tool use, GGUF, ONNX, MLX, llama.cpp and LM Studio support. Open-weight under LFM 1.0.
chatcodereasoningspeedstandardgeneral
Mac mini M4
Best local LLMs for Mac mini M4
Practical local AI picks for Mac mini M4 and M4 Pro machines, focused on unified memory, LM Studio fit and real desktop workflows.
Quick answer
For a Mac mini M4 with 16GB, start with compact 8B-14B class models and keep enough memory headroom for macOS and LM Studio. For M4 Pro 24GB or 48GB, larger 24B-32B class models become more comfortable.
Recommended starting points
#2
Granite 4.1 (8B)
IBM Granite 4.1 long-context instruct model. Apache 2.0, 131K context, tool calling, RAG, code tasks, multilingual dialog and business assistant workflows on normal 8-16 GB machines.
chatcodereasoningstandardgeneral
#3
GLM 4.6 Air (12B)
Zhipu AI lightweight flagship. Strong bilingual CN/EN with hybrid thinking mode, 200K context and tool calling. Apache 2.0 — excellent alternative to Qwen 3.5 9B on modest GPUs.
chatcodereasoningstandardgeneral
#4
GLM 4.5 Air (MoE)
Zhipu AI's efficient MoE powerhouse. 106B total parameters, only 14B active at inference — dense-model speed with much larger model quality. Clearly the best in the 16–24GB RAM range. Outperforms Llama 3.3 70B. Apache 2.0.
chatcodepowerqualitygeneral
#5
Nemotron Nano 9B v2
NVIDIA hybrid Mamba-Transformer 9B. 6x throughput vs comparable dense models, 128K context, strong maths/code. Efficient toggle-able reasoning. NVIDIA Open Model License.
chatreasoningcodestandardgeneral
#6
Qwen 3 (14B)
The sweet spot. Incredible reasoning, coding and chat quality. The best model you can run on 16GB.
chatcodereasoningpowergeneral
#7
Apriel Nemotron 15B Thinker
ServiceNow x NVIDIA mid-size reasoner. Half the memory of 32B reasoners with comparable performance on MBPP, BFCL, GPQA. Strong enterprise fit. MIT licensed.
reasoningcodepowergeneral
#8
Llama-3.1-Nemotron-Nano (4B)
⭐ Mac Mini M4 16GB top pick! NVIDIA fine-tune of Llama 3.1. Hybrid /think • /no_think mode — deep reasoning on demand, instant chat otherwise. ~80–120 tok/s on Apple Silicon Metal. 128K context. Apache 2.0.
chatlightspeedreasoning
#9
Qwen 3.6 (6.7B)
Alibaba's hybrid-thinking micro-flagship. Toggles between instant answers and deep chain-of-thought reasoning on demand. 128K context, 29 languages, outperforms Qwen3-8B on reasoning benchmarks. Apache 2.0.
chatcodereasoningspeedgeneral
Keep exploring
Source checks
These guides use LocalClaw's internal model database for scoring, then avoid hard claims beyond public hardware and model availability signals checked before publishing.