LTM Models by Magic
2 models2023–2024Up to 100m ctx
Details
ResearcherMagic
LicenseProprietary
Commercial useCommercial use with conditions
Models2
Released2023–2024
Max context100m
Links
WebsiteAbout
LTM (Long-Term Memory) is Magic's model family focused on extreme-scale context windows for software development. LTM-1 (2023) introduced a 5M-token context; LTM-2-mini (2024) extended this to 100M tokens using a novel sequence-dimension algorithm. Developed by Magic (magic.dev), San Francisco.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
LTM-2-miniCurrent
Use when the workload needs code, 100m context, and coding.
2024-08code100m contextcoding
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LTM-2-mini | Use when the workload needs code, 100m context, and coding. | 2024-08 | code100m contextcoding | Current |
| LTM-1 | Use when the workload needs code, 5m context, and coding. | 2023-06 | code5m contextcoding | Current |
Release Timeline
2 release groups2024-08
1 current
LTM-2-mini
Currentcode100m contextcoding
2023-06
1 current
LTM-1
Currentcode5m contextcoding
Specifications(2 models)
| Model | Released | Context |
|---|---|---|
| LTM-2-mini | 2024-08 | 100m |
| LTM-1 | 2023-06 | 5m |
Frequently Asked Questions
- What is LTM used for?
- LTM is used for coding and code. The family description and listed model capabilities point to those workloads as the best fit.
- How does LTM compare to StarCoder?
- LTM by Magic is strongest where you need coding, while StarCoder by ServiceNow Research is the closest related family to check for coding. LTM has 2 listed variants and reaches up to 100m context, while StarCoder reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which LTM model should I use?
- If price is the main constraint, use the pricing table first because LTM does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate LTM-2-mini with 100m context.
