Magnum Models
Llama 3 CommunityOpen weights
1 model2024Up to 16k ctx
Last refreshed 2026-05-19. Next refresh: weekly.
Details
LicenseLlama 3 Community
Commercial useCommercial use: conditional
Models1
Released2024
Max context16k
Links
WebsiteAbout
Magnum is a series of fine-tuned roleplay and creative writing models by anthracite-org on HuggingFace, built on top of Qwen and Llama base models.
Decision facts
- Best fit
- General model comparison
- Capability starting point
- Magnum v4 72B with 16k context
- Lowest tracked input
- Not tracked
- Closest related family
- Claude 3
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Magnum v4 72BCurrent
Use when the workload needs 16k context and 72B parameters.
2024-0916k context72B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Magnum v4 72B | Use when the workload needs 16k context and 72B parameters. | 2024-09 | 16k context72B parameters | Current |
Release Timeline
1 release group2024-09
1 current
Magnum v4 72B
Current16k context72B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Magnum v4 72B | 2024-09 | 16k | 72B |