What is the best local model for coding on the Apple M3 Max?

On the Apple M3 Max, lmstudio-community/GLM-4.7-Flash-GGUF:Q4_K_M ranks first for coding in our benchmarks (63.4/100 at ~36.2 tok/s).

What is the best local model for agentic workflows on the Apple M3 Max?

On the Apple M3 Max, lmstudio-community/GLM-4.7-Flash-GGUF:Q4_K_M ranks first for agentic workflows in our benchmarks (77.2/100 at ~36.2 tok/s).

Hardware Benchmarks

Compare Apple M3 Max benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

Apple M3 Max

Models we recommend for Apple M3 Max.

Fastest & Largest context

852.88M

223.0 tok/sContext 8,192 tokens

Highest token generation speed at 223.0 tok/s. Largest context that fits in 64GB VRAM, at 8,192 tokens.

Best quality

Unknown

36.2 tok/sQuality 73.2

Highest completed quality score at 73.2.

Which models actually run best on the Apple M3 Max, by task, from community benchmark data.

What is the best local model for coding on the Apple M3 Max?: On the Apple M3 Max, lmstudio-community/GLM-4.7-Flash-GGUF:Q4_K_M ranks first for coding in our benchmarks (63.4/100 at ~36.2 tok/s).
What is the best local model for agentic workflows on the Apple M3 Max?: On the Apple M3 Max, lmstudio-community/GLM-4.7-Flash-GGUF:Q4_K_M ranks first for agentic workflows in our benchmarks (77.2/100 at ~36.2 tok/s).

Completed quality-ranked benchmark results for Apple M3 Max.