Macs
Which AI models run on the M5 (16 GB, 8-core GPU)?
The M5 (16 GB, 8-core GPU) has 16 GB of memory, about 10.7 GB of it usable for a model, and 153 GB/s of memory bandwidth. 43 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026 · Vendor specs
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Nemotron Nano 9B v29B | Q6_K | 8.6 GB | ~11 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q4_K_M | 8.2 GB | ~26 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~29 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~30 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~14 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~50 tok/s our est. |
| Gemma 4 12B12B | Q4_K_M | 9.2 GB | ~17 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q4_K_M | 7.5 GB | ~22 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~18 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~26 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~25 tok/s ModelFit est. |
| Jebadiah 9B9B | Q5_K_M | 7.8 GB | ~22 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~23 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~19 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~25 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~21 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~75 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~16 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~15 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~22 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~16 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~29 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~17 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~26 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~29 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~34 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~26 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~28 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~53 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~38 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~61 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~51 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~52 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~61 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~59 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~62 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~105 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~109 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~125 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~110 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~135 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~231 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~131 tok/s ModelFit est. |
Speeds come from ModelFit's estimates (CC BY 4.0) where it covers the model, otherwise from our bandwidth formula. Method
Too big for this machine
Mistral Nemo 12B (10.7 GB), Gemma 3 12B Instruct (10.7 GB), Qwen2.5 14B Instruct (12.3 GB), Phi-3 Medium 14B (12.3 GB), Qwen2.5 Coder 14B (12.3 GB), Qwen3 14B (12.3 GB), DeepSeek-R1 Distill Qwen 14B (12.3 GB), Phi-4 14B (12.8 GB), gpt-oss-20b (15.1 GB), LFM2 24B-A2B Instruct (15.3 GB), Mistral Small 3.1 (16.4 GB), Devstral Small 2 24B (16.6 GB) and more.
Questions
What is the best AI model for the M5 (16 GB, 8-core GPU)?
Qwen3.5 9B Instruct at Q4_K_M: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 26 tok/s, ModelFit est.).
How much memory can a model use on the M5 (16 GB, 8-core GPU)?
About 10.7 GB of the 16 GB.
How fast is the M5 (16 GB, 8-core GPU) for local LLMs?
Decode speed is limited by memory bandwidth: 153 GB/s. A model that reads 10 GB per token runs at under 15 tokens per second.