Fastest & Best quality & Largest context
gpt-oss:20b
20.9B
25.3 tok/sQuality 78.7Context 8,192 tokens
Highest token generation speed at 25.3 tok/s. Highest completed quality score at 78.7. Largest context that fits in 32GB VRAM, at 8,192 tokens.
Hardware Benchmarks
Best Local LLM Performance for Apple M4
Compare Apple M4 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 M4.
Frequently asked questions
Which models actually run best on the Apple M4, by task, from community benchmark data.
- What is the best local model for coding on the Apple M4?
- On the Apple M4, gpt-oss:20b ranks first for coding in our benchmarks (76.2/100 at ~25.3 tok/s).
- What is the best local model for agentic workflows on the Apple M4?
- On the Apple M4, gpt-oss:20b ranks first for agentic workflows in our benchmarks (80.4/100 at ~25.3 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for Apple M4.