M4 Max (48 GB) — benchmark record

M4 Max (48 GB) local LLM benchmarks on Apple Silicon Mac with 9 published rows across 9 models. Peak published speed is 125.0 tok/s on Phi-4 Mini Instruct 3.8B. Published runtimes include LM Studio, MLX, Ollama.

9Benchmark rows

9Models tested

125.0Fastest avg tok/s (Phi-4 Mini Instruct 3.8B)

0Lab benchmarks

Quick take

Best published speed here is 125.0 tok/s on Phi-4 Mini Instruct 3.8B at Q4_K - Medium. This page is evidence, not the full buying answer.

Based on 9 external benchmarks; no lab runs yet.

Published runtimes: LM Studio, MLX, Ollama.

Need a recommendation? Use Buy Checking a target model? Use Fit Want a setup answer? Use Run Browse Macs by exact hardware Need the full audit trail? Use Bench

Current published coverage

Published model coverage includes Phi-4 Mini Instruct 3.8B, Qwen3.6-35B-A3B, Qwen 3 30B-A3B, Gemma 4 26B-A4B plus 5 more published models. Published runtime coverage on this chip includes LM Studio, MLX, Ollama. Fastest published row is 125.0 tok/s on Phi-4 Mini Instruct 3.8B at Q4_K - Medium.

Phi-4 Mini Instruct 3.8B Qwen3.6-35B-A3B Qwen 3 30B-A3B Gemma 4 26B-A4B Gemma 3 27B Qwen3.5-35B-A3B

Other published M4 Max variants: GB · 64 GB · 128 GB

Macs shipping with the M4 Max (48 GB)

MacBook Pro M4 Max 36GB 14-inch MacBook Pro M4 Max 48GB 14-inch MacBook Pro M4 Max 36GB 16-inch MacBook Pro M4 Max 48GB 16-inch MacBook Pro M4 Max 64GB 16-inch MacBook Pro M4 Max 128GB 16-inch Mac Studio M4 Max 36GB Mac Studio M4 Max 48GB Mac Studio M4 Max 64GB Mac Studio M4 Max 128GB

This chip is part of a family. Compare all M4 Max RAM variants →

Raw benchmark rows for M4 Max (48 GB)

Rows sorted by avg tok/s descending. Click source badge to see original measurement page.

Model	Quant	RAM req.	Context	Avg tok/s	Prompt tok/s	Runtime	Source
Phi-4 Mini Instruct 3.8B	Q4_K - Medium	—	—	125.0 tok/s	—	MLX	ref
Qwen3.6-35B-A3B	Q4_K - Medium	—	—	42.0 tok/s	—	MLX	ref
Qwen 3 30B-A3B	Q4_K - Medium	—	—	42.0 tok/s	—	Ollama	ref
Gemma 4 26B-A4B	Q4_K - Medium	—	—	40.0 tok/s	—	MLX	ref
Gemma 3 27B	Q4_K - Medium	—	—	35.0 tok/s	—	MLX	ref
Qwen3.5-35B-A3B	Q4_K - Medium	—	—	34.0 tok/s	—	Ollama	ref
Nemotron Cascade 2 30B-A3B	Q4_K - Medium	—	—	28.0 tok/s	—	MLX	ref
Gemma 4 31B	Q4_K - Medium	—	—	18.0 tok/s	—	MLX	ref
DeepSeek R1 Distill Qwen 32B	Q4_K - Medium	—	—	18.0 tok/s	—	LM Studio	ref

Models tested on this chip

Phi-4 Mini Instruct 3.8B Qwen3.6-35B-A3B Qwen 3 30B-A3B Gemma 4 26B-A4B Gemma 3 27B Qwen3.5-35B-A3B Nemotron Cascade 2 30B-A3B Gemma 4 31B DeepSeek R1 Distill Qwen 32B

Next step

Use Rankings when you need the best overall answer for a Mac, and keep this page open when you need the evidence behind that recommendation.

If you are comparing local Apple Silicon against rented cloud hardware, use AI Data Center Index for current GPU rental context.

Data

benchmarks.json — full dataset · chips.json — chip summaries · benchmarks.csv — CSV export

Data from in-house lab measurements plus community-published benchmarks. See all chip families →