M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling): edge AI benchmarks
Key results
| Workload | Best result | Model · precision | Power · perf/W | Grade · date | Source |
|---|---|---|---|---|---|
| LLM generation | 59.38 tok/s batch 1 | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | unknown | D 2026-09-22 (page last edited) | Jeff Geerling ai-benchmarks README (Findings tables) |
Best published result per workload, across model sizes. For like-for-like groups, open the per-workload tables below.
Show data — per-workload tables
object detection
No published object detection results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
instance segmentation
No published instance segmentation results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
pose estimation
No published pose estimation results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
image classification
No published image classification results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
semantic segmentation
No published semantic segmentation results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
speech-to-text
No published speech-to-text results for M1 Max Mac Studio (10 core - 64GB) (as tested by Jeff Geerling) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
LLM generation
| Like-for-like group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| LLM ≤4B · b=1 | 59.38 tok/s | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | D | unknown power n/a | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) | 39 of 65 |
| LLM >40B · b=1 | 7.25 tok/s | Llama 3.1:70b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | D | unknown power n/a | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) | 5 of 11 |
How to read these numbers
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.