Updated 59 min ago · first seen 11 Sept 2026
hw_01M293SPJHZDNNEV8Z5P2NS4WQ
- Kind
- soc
- T2 · 59 min ago
- Bandwidth
- 400 GB/s
- T2 · 59 min ago
- Released
- Jan 2023
- T2 · 59 min ago
Specification
- Release date
- Jan 2023
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Kind
- soc
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Manufacturer
- Apple
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Memory bandwidth
- 400 GB/s
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Memory
- 32, 64, 96
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Runtimes
- mlx, llama.cpp, coreml
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
- Spec sheet
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 59 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
7
Source tiers
T27
Freshest observation
59 min ago
Conflicts
None
Models whose estimated memory footprint fits this device — see estimate method.
No models recorded
- Manufactured by
- Apple
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Memory
Memorymemory_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 32, 64, 96 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
No documents recorded