MetaComputing AI PC Framework 13 Mainboard (as tested by Jeff Geerling): edge AI benchmarks
Key results
| Workload | Best result | Model · precision | Power · perf/W | Grade · date | Source |
|---|---|---|---|---|---|
| LLM generation | 13.10 tok/s CPU-only batch 1 | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | 29.00 W (measured) 0.452 tok/s/W | C 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 MetaComputing AI PC Framework 13 Mainboard (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 MetaComputing AI PC Framework 13 Mainboard (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 MetaComputing AI PC Framework 13 Mainboard (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 MetaComputing AI PC Framework 13 Mainboard (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 MetaComputing AI PC Framework 13 Mainboard (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 MetaComputing AI PC Framework 13 Mainboard (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 5–14B · b=1 | 3.25 tok/s CPU-only | DeepSeek R1 14b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | C | 32.00 W measured | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) | 51 of 54 |
| LLM 15–40B · b=1 | 8.52 tok/s CPU-only | gpt-oss 20b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | C | 27.00 W measured | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) | 22 of 22 |
| LLM ≤4B · b=1 | 13.10 tok/s CPU-only | Llama 3.2:3b as in linked issue (Ollama default tags are 4-bit) · Ollama / llama.cpp (see linked issue) | C | 29.00 W measured | Jeff Geerling ai-benchmarks README (Findings tables) 2026-09-22 (page last edited) | 56 of 65 |
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.