System · laptop

MacBook Pro M4 Max 128 GB

Runs models up to ~160B parameters at 4-bit in unified memory. Laptop with 128 GB unified memory.

Unified memory: 128 GB
System RAM: Shared
Runs: 18 of 19model variants, 8K
Estimated cost: ~$5,400

What it runs

Largest models that fit without spilling into system memory, at an 8K contextHow much text the model can consider at once, counted in tokens — roughly ¾ of a word each..

Everything →

Variant
Llama 3.1 70B Instruct
70.6B · Q4_K_M via llama.cpp
Runs well
~8 tok/s est.
Variant
Llama 3.3 70B Instruct
70.6B · Q4_K_M via llama.cpp
Runs well
~8 tok/s est.
Variant
Mixtral 8x7B Instruct v0.1
46.7B · Q4_K_M via llama.cpp
Runs well
~42 tok/s est.
Variant
Qwen2.5 32B Instruct
32.8B · Q5_K_M via llama.cpp
Runs well
~15 tok/s est.
Variant
Qwen2.5-Coder 32B Instruct
32.8B · Q8_0 via llama.cpp
Runs well
~10 tok/s est.
Variant
DeepSeek-R1-Distill-Qwen-32B
32.8B · Q4_K_M via llama.cpp
Runs well
~17 tok/s est.
Variant
Qwen3 30B-A3B
30.5B · Q8_0 via llama.cpp
Runs well
~88 tok/s est.
Variant
Gemma 3 27B IT
27.4B · Q4_K_M via llama.cpp
Runs well
~21 tok/s est.
Variant
Gemma 2 27B IT
27.2B · Q4_K_M via llama.cpp
Runs well
~21 tok/s est.
Variant
Mistral Small 24B Instruct 2501
23.6B · Q6_K via llama.cpp
Runs well
~18 tok/s est.

Components

1× Hardware Apple M4 Max (40-core GPU) soc

Measured performance

Model · quantization	Runtime	Context	Measurements	Source
Llama 3.3 70B Instruct MLX 4-bit (MLX Community)	MLX-LMmetal · 0.21.0	4K	11.2 tok/s · Generation throughput 41 GB · Peak memory 110 tok/s · Prompt throughput 4,200 ms · Time to first token	Mutinai illustrative fixtures

Community results

Contributions are not open yet, so there is nothing here from members.

Reviews

Contributions are not open yet, so there is nothing here from members.