Fastest
Qwen2.5-Coder-0.5B-Instruct-oQ8e-fp16
0.5B
169.1 tok/s
Highest token generation speed at 169.1 tok/s.
Hardware Benchmarks
Best Local LLM Performance for Apple M1 Pro
Compare Apple M1 Pro benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 32GB
Recommended Models
Models we recommend for Apple M1 Pro.
Best quality
gemma4:31b
31.3B
2.4 tok/sQuality 75.3
Highest completed quality score at 75.3.
Largest context
gemma4:12b
11.9B
13.9 tok/sContext 65,536 tokens
Largest context that fits in 32GB VRAM, at 65,536 tokens.
Frequently asked questions
Which models actually run best on the Apple M1 Pro, by task, from community benchmark data.
- What is the best local model for coding on the Apple M1 Pro?
- On the Apple M1 Pro, MiMo-V2.6-Distill-Qwen-9B-oQ8e-fp16 ranks first for coding in our benchmarks (76.2/100 at ~19.6 tok/s).
- What is the best local model for agentic workflows on the Apple M1 Pro?
- On the Apple M1 Pro, gemma4:12b ranks first for agentic workflows in our benchmarks (76.1/100 at ~13.9 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for Apple M1 Pro.