Memory
As an Amazon Associate, I earn from qualifying purchases.
Best for general use
Highest MMLU score among models that run well
- Qwen3 Next 80B-A3B Q4_K_M 256K context · ~78 tok/s · MMLU 90
- Qwen3.6 27B Q8_0 256K context · ~9 tok/s · MMLU 86.2
- Qwen 2.5 72B Q4_K_M 65K context · ~6 tok/s · MMLU 86.1
Best for coding
Highest SWE-bench Verified score among models that run well
- Qwen3.8 27B Q8_0 256K context · ~9 tok/s · SWE-bench 86
- Ornith 1.5 35B A3B Q8_0 256K context · ~56 tok/s · SWE-bench 79
- Qwen3.6 27B Q8_0 256K context · ~9 tok/s · SWE-bench 77.2
Upgrade options
The cheapest GPUs with more VRAM than the M4 Pro, by launch MSRP.
As an Amazon Associate, I earn from qualifying purchases.
Every model on the M4 Pro (64 GB)
154 of 214 model configurations can run on 64 GB — sorted by quality
107 models, each counted once by the best way it runs on your hardware.
Largest that runs well Llama 4 Scout 109B params · Q4_K_M · 17K context Fastest good-quality model Phi-3 Mini 3.8B ~80 tok/s · Q4_K_M · 128K context Runs well 77
Tight fit 2
-
Q4_K_M Context 8K Speed ~15 tok/s
Only 8K context — under the 16K needed to be practical
Q8_0 Context 8K Speed ~9 tok/s
Only 8K context — under the 16K needed to be practical
-
Q4_K_M Context 8K Speed ~40 tok/s
Only 8K context — under the 16K needed to be practical
Q8_0 Context 8K Speed ~25 tok/s
Only 8K context — under the 16K needed to be practical
Notify me when new models fit my GPU
An email when a new model fits your M4 Pro — no spam, unsubscribe anytime.
Doesn't fit 28
-
Q4_K_M Needs 381.2 GB — 317.2 GB over
Q8_0 Needs 664.4 GB — 600.4 GB over
-
Q4_K_M Needs 586.5 GB — 522.5 GB over
Q8_0 Needs 1013.0 GB — 949.0 GB over
-
Q4_K_M Needs 68.2 GB — 4.2 GB over
Q8_0 Needs 118.3 GB — 54.3 GB over
GPUs that can run this
As an Amazon Associate, I earn from qualifying purchases.